A Digital Twin with Transfer Learning Enables Cross-Anatomical Forecasting of Postmortem Microbiome Dynamics for PMI Estimation

A Digital Twin with Transfer Learning Enables Cross-Anatomical Forecasting of Postmortem Microbiome Dynamics for PMI Estimation | 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 A Digital Twin with Transfer Learning Enables Cross-Anatomical Forecasting of Postmortem Microbiome Dynamics for PMI Estimation Kang Ning, Jin Han, Yuli Zhang, Haohong Zhang, Kouyi Zhou, Xiaoke Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8670931/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Forensic microbiology leverages postmortem microbiome succession as a promising biomarker for estimating the postmortem interval (PMI). However, current methods are constrained by sparse sampling (typically 3–5 time points) and poor cross-anatomical generalizability, leading to imprecise PMI estimates with errors often exceeding ± 3 days, particularly in cases of dismembered remains. To overcome these, we developed mHolmes, a transformer-based digital twin framework powered by transfer learning. Trained on high-resolution data from 34 cadavers over 21 days, mHolmes achieves accurate daily predictions of microbial dynamics, reducing errors and demonstrating high accuracy (MAE < ± 2 days) in cross-anatomical forecasting (e.g., hip to face). Shapley Additive exPlanations (SHAP) analysis ensures interpretability by identifying seven key bacterial classes as conserved biomarkers. This study highlights mHolmes as a robust, high-precision tool that addresses critical bottlenecks, enabling reliable PMI estimation from incomplete data with significant applications in forensic investigations, such as body part matching and daily-resolution timeline reconstruction. Biological sciences/Microbiology/Microbial communities/Microbial ecology Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Microbiology/Applied microbiology Digital twin Transfer learning Forensic microbiology Postmortem interval Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryMaterials.docx supplementary material Cite Share Download PDF Status: Under Review 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-8670931","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":581863034,"identity":"ab34a18c-16b6-44b5-9d76-11350515f2e3","order_by":0,"name":"Kang Ning","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYDACZgYGxgYgzS8B4YM5xGmRnAEkDhClBWawwQ1itZiz8x5+OaPmjt3m2z3Gnz8w2MhuOMD87AE+LZbNfGmWG449S95254yZxAGGNOMNB9jMDfBpMTjMY2b4gO1wstmNHDOgww4nbjjAwyZBWMu/w8nGM3KMPxxg+E+UFuOHG9sO2xlI5BgAHXaAOFsYZ/YdTpC4kVYmccYg2XjmYTYz/FrOnzH+2PPtsD3/jOTNHyoq7GT7jjc/w6sFCMDOSGyAmMAAjlxCgPkDkLAnrG4UjIJRMApGLAAAo3BPiXJwgGgAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-3325-5387","institution":"Huazhong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Kang","middleName":"","lastName":"Ning","suffix":""},{"id":581863035,"identity":"0657ec4c-efd6-4f6e-8042-05348f63e161","order_by":1,"name":"Jin Han","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jin","middleName":"","lastName":"Han","suffix":""},{"id":581863036,"identity":"947ea0ad-26b1-4799-951d-73d3d1682862","order_by":2,"name":"Yuli Zhang","email":"","orcid":"https://orcid.org/0009-0009-3685-8360","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yuli","middleName":"","lastName":"Zhang","suffix":""},{"id":581863037,"identity":"1279dcf8-0426-4b08-980b-1e5102122c5e","order_by":3,"name":"Haohong Zhang","email":"","orcid":"https://orcid.org/0000-0001-6267-4244","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Haohong","middleName":"","lastName":"Zhang","suffix":""},{"id":581863038,"identity":"3ce04bed-cf5b-41ef-82d7-6eea191e9dd7","order_by":4,"name":"Kouyi Zhou","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Kouyi","middleName":"","lastName":"Zhou","suffix":""},{"id":581863039,"identity":"192de758-eecc-4aa0-a531-bbe24dc28534","order_by":5,"name":"Xiaoke Chen","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaoke","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2026-01-22 14:35:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8670931/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8670931/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101398596,"identity":"157832cc-2b0c-4855-a85d-9a6316b0a014","added_by":"auto","created_at":"2026-01-29 09:42:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1279733,"visible":true,"origin":"","legend":"","description":"","filename":"mHolmesmanuscript20260121.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8670931/v1_covered_065bd789-c8fa-4b47-901e-518f4a1ff2ea.pdf"},{"id":101385989,"identity":"e5c0b91a-0420-44c1-9092-8bfc4dcf5f31","added_by":"auto","created_at":"2026-01-29 07:19:50","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":940397,"visible":true,"origin":"","legend":"\u003cp\u003esupplementary material\u003c/p\u003e","description":"","filename":"SupplementaryMaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-8670931/v1/5769d1d43d46b3cde55fadf7.docx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A Digital Twin with Transfer Learning Enables Cross-Anatomical Forecasting of Postmortem Microbiome Dynamics for PMI Estimation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Digital twin, Transfer learning, Forensic microbiology, Postmortem interval","lastPublishedDoi":"10.21203/rs.3.rs-8670931/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8670931/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eForensic microbiology leverages postmortem microbiome succession as a promising biomarker for estimating the postmortem interval (PMI). However, current methods are constrained by sparse sampling (typically 3\u0026ndash;5 time points) and poor cross-anatomical generalizability, leading to imprecise PMI estimates with errors often exceeding\u0026thinsp;\u0026plusmn;\u0026thinsp;3 days, particularly in cases of dismembered remains. To overcome these, we developed mHolmes, a transformer-based digital twin framework powered by transfer learning. Trained on high-resolution data from 34 cadavers over 21 days, mHolmes achieves accurate daily predictions of microbial dynamics, reducing errors and demonstrating high accuracy (MAE\u0026thinsp;\u0026lt;\u0026thinsp;\u0026plusmn;\u0026thinsp;2 days) in cross-anatomical forecasting (e.g., hip to face). Shapley Additive exPlanations (SHAP) analysis ensures interpretability by identifying seven key bacterial classes as conserved biomarkers. This study highlights mHolmes as a robust, high-precision tool that addresses critical bottlenecks, enabling reliable PMI estimation from incomplete data with significant applications in forensic investigations, such as body part matching and daily-resolution timeline reconstruction.\u003c/p\u003e","manuscriptTitle":"A Digital Twin with Transfer Learning Enables Cross-Anatomical Forecasting of Postmortem Microbiome Dynamics for PMI Estimation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-29 07:19:44","doi":"10.21203/rs.3.rs-8670931/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"785b56ec-96f5-4bf4-b733-9a0c4a24b578","owner":[],"postedDate":"January 29th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":61904917,"name":"Biological sciences/Microbiology/Microbial communities/Microbial ecology"},{"id":61904918,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":61904919,"name":"Biological sciences/Microbiology/Applied microbiology"}],"tags":[],"updatedAt":"2026-04-29T14:36:33+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-29 07:19:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8670931","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8670931","identity":"rs-8670931","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}