Early Identification of High-Risk Patients with HCC Relapse: A Spatial Immune Scoring System Enabled by Artificial Intelligence

Early Identification of High-Risk Patients with HCC Relapse: A Spatial Immune Scoring System Enabled by Artificial Intelligence | 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 Biological Sciences - Article Early Identification of High-Risk Patients with HCC Relapse: A Spatial Immune Scoring System Enabled by Artificial Intelligence cheng Sun, Gengjie Jia, Peiqi He, Denise Goh, Fuling Li, Felicia Wee, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2707861/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 12 Mar, 2025 Read the published version in Nature → Version 1 posted You are reading this latest preprint version Abstract Given the high prevalence and relapse rates of hepatocellular carcinoma (HCC), an increased capacity for early identification of patients most at risk for post-resection recurrence would help improve patient outcomes and prioritize health care resources. Here, we combined spatial multi-transcriptomics and proteomics approaches to characterize the tumor and immunological landscape of 61 samples. We observed a spatial and HCC-recurrence-associated distribution of natural killer (NK) cells in the invasive front and tumor center. Using artificial-intelligence alongside an extreme gradient-boosting algorithm, we developed the Tumor Immune MicroEnvironment Spatial (“TIMES”) score based on the expression of five NK-associated markers (SPON2, ZFP36L2, ZFP36, VIM, and HLA-DRB1) to predict HCC recurrence. We also demonstrated that TIMES score (HR = 29.6, P < 0.001) outperforms the current standard tools for patient risk stratification including the TNM (HR = 1.93, P = 0.113) and BCLC (HR = 1.55, P = 0.253) systems. In the clinic, we validated the model in 103 patients from three multi-centered cohorts achieve a real-world sensitivity of 90.00% and specificity of 90.24%. In the lab, following up on the individual marker with the highest prediction accuracy, in vivo models revealed that SPON2 increases IFN-γ secretion and enhances infiltration potential of NK cells at the invasive front. Additionally, we established the TIMES score on a publicly accessible website that can be easily achieved by different levels of pathology labs to facilitate global prediction of HCC recurrence risk and stratification of high-risk patients. With its ability to efficiently stratify high-risk patients, it exemplifying the utility of artificial intelligence to improve our understanding on TIME features that underlie tumor progression. Health sciences/Diseases/Cancer/Cancer microenvironment Biological sciences/Immunology/Lymphocytes/NK cells Health sciences/Diseases/Cancer/Tumour immunology/Immunosurveillance Biological sciences/Cancer/Cancer prevention Full Text Additional Declarations There is NO Competing Interest. Supplementary Files ExtendedVideo1NK92normal.mp4 Extended Video1 NK92 norma ExtendedVideo2NK92pcSLentiSPON2.mp4 Extended Video2 NK92-pcSLenti-SPON2 Cite Share Download PDF Status: Published Journal Publication published 12 Mar, 2025 Read the published version in Nature → 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-2707861","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Biological Sciences - Article","associatedPublications":[],"authors":[{"id":188069710,"identity":"22962faf-e873-43e6-9e04-dfe8eec2cb7f","order_by":0,"name":"cheng Sun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2klEQVRIiWNgGAWjYDACCSB+AMT8UD5jA1FaEoBYsgGimgQtBgeI1cI/u/nZh4SKOnvjG+nPH/xgsJHdcID52QO8ltw5Zjwj4czhxG03cgwbexjSjDccYDM3wKfFQCLBmCGx7UCC2Y0cxmYGhsOJGw7wsEng15L+mSHxH9BhM9IfArX8J0ZLDtCWBmbGDRIJhkAtBwhrkbiRU8yQcOxw4owzbwxn9hgkG888zGaGVwv/jPTNDB9q6uz529MffPhRYSfbd7z5GV4t6O4EYmYS1I+CUTAKRsEowA4Au0pJ8/LpamQAAAAASUVORK5CYII=","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":true,"prefix":"","firstName":"cheng","middleName":"","lastName":"Sun","suffix":""},{"id":188069711,"identity":"9558aa5e-498c-46e0-9fd3-429a8e704fc0","order_by":1,"name":"Gengjie Jia","email":"","orcid":"","institution":"Agricultural Genomics Institute at Shenzhen","correspondingAuthor":false,"prefix":"","firstName":"Gengjie","middleName":"","lastName":"Jia","suffix":""},{"id":188069712,"identity":"ac2a442a-df76-43bb-8525-78dd1ede275e","order_by":2,"name":"Peiqi He","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Peiqi","middleName":"","lastName":"He","suffix":""},{"id":188069713,"identity":"9329fbef-022a-4b03-8572-985c29231412","order_by":3,"name":"Denise Goh","email":"","orcid":"https://orcid.org/0000-0003-4598-4181","institution":"Institute of Molecular and Cell Biology (IMCB), Agency for Science, Technology and Research (A*STAR), Republic of Singapore","correspondingAuthor":false,"prefix":"","firstName":"Denise","middleName":"","lastName":"Goh","suffix":""},{"id":188069714,"identity":"c5b87c22-8548-426e-b500-7245efb44ab5","order_by":4,"name":"Fuling Li","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Fuling","middleName":"","lastName":"Li","suffix":""},{"id":188069715,"identity":"8d2e4b9e-717c-4221-88f7-9d610a0d897f","order_by":5,"name":"Felicia Wee","email":"","orcid":"","institution":"Institute of Molecular and Cell Biology (IMCB), Agency for Science, Technology and Research (A*STAR), Republic of Singapore","correspondingAuthor":false,"prefix":"","firstName":"Felicia","middleName":"","lastName":"Wee","suffix":""},{"id":188069716,"identity":"7da1d5ed-dec8-4bd9-822b-72cf438a3d1e","order_by":6,"name":"Mengyuan Sun","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Mengyuan","middleName":"","lastName":"Sun","suffix":""},{"id":188069717,"identity":"9ac0ff71-079e-43ad-bf89-7e1d72fd34bb","order_by":7,"name":"Tianli Dai","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Tianli","middleName":"","lastName":"Dai","suffix":""},{"id":188069718,"identity":"13649b0a-25f3-4d65-b78f-32ca53a86df2","order_by":8,"name":"Jeffrey LIM","email":"","orcid":"","institution":"Institute of Molecular and Cell Biology (IMCB), Agency for Science, Technology and Research (A*STAR), Republic of Singapore","correspondingAuthor":false,"prefix":"","firstName":"Jeffrey","middleName":"","lastName":"LIM","suffix":""},{"id":188069719,"identity":"2372df9a-d0e1-4ef9-ba42-78ca444f30b9","order_by":9,"name":"Shuxia Hao","email":"","orcid":"","institution":"Agricultural Genomics Institute at Shenzhen","correspondingAuthor":false,"prefix":"","firstName":"Shuxia","middleName":"","lastName":"Hao","suffix":""},{"id":188069720,"identity":"84962c93-e6ac-47b8-b470-db3bd8c11b0f","order_by":10,"name":"Lianxin Liu","email":"","orcid":"https://orcid.org/0000-0002-3535-6467","institution":"The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Lianxin","middleName":"","lastName":"Liu","suffix":""},{"id":188069721,"identity":"110b70db-949c-4d99-a99e-5c643523d526","order_by":11,"name":"Joe Yeong","email":"","orcid":"","institution":"Institute of Molecular and Cell Biology (IMCB), Agency for Science, Technology and Research (A*STAR), Republic of Singapore","correspondingAuthor":false,"prefix":"","firstName":"Joe","middleName":"","lastName":"Yeong","suffix":""},{"id":188069722,"identity":"8ab62f3b-07ef-45dc-919b-542d2b5e4d69","order_by":12,"name":"Zhigang Tian","email":"","orcid":"https://orcid.org/0000-0002-5512-6378","institution":"University of Science \u0026 Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Zhigang","middleName":"","lastName":"Tian","suffix":""}],"badges":[],"createdAt":"2023-03-18 11:30:48","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2707861/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2707861/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41586-025-08668-x","type":"published","date":"2025-03-12T04:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":78429180,"identity":"036aa536-7c99-4be1-90bb-0507d18febcd","added_by":"auto","created_at":"2025-03-13 07:05:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":13310559,"visible":true,"origin":"","legend":"Article File","description":"","filename":"article.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2707861/v1_covered_e65b1b4e-a0a8-47f0-922a-b80f7a454cb7.pdf"},{"id":35173548,"identity":"00609f4f-8492-416c-88b5-10cdcb9dcddf","added_by":"auto","created_at":"2023-04-03 02:51:35","extension":"mp4","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":30009912,"visible":true,"origin":"","legend":"\u003cp\u003eExtended Video1 NK92 norma\u003c/p\u003e","description":"","filename":"ExtendedVideo1NK92normal.mp4","url":"https://assets-eu.researchsquare.com/files/rs-2707861/v1/d5e9974d6d75d78d47199a4a.mp4"},{"id":35173529,"identity":"91ec609c-c73d-472b-a0e6-b98b3397f798","added_by":"auto","created_at":"2023-04-03 02:51:34","extension":"mp4","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":1754573,"visible":true,"origin":"","legend":"\u003cp\u003eExtended Video2 NK92-pcSLenti-SPON2\u003c/p\u003e","description":"","filename":"ExtendedVideo2NK92pcSLentiSPON2.mp4","url":"https://assets-eu.researchsquare.com/files/rs-2707861/v1/8bee1395bd92c270985435ad.mp4"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Early Identification of High-Risk Patients with HCC Relapse: A Spatial Immune Scoring System Enabled by Artificial Intelligence","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-2707861/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2707861/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Given the high prevalence and relapse rates of hepatocellular carcinoma (HCC), an increased capacity for early identification of patients most at risk for post-resection recurrence would help improve patient outcomes and prioritize health care resources. Here, we combined spatial multi-transcriptomics and proteomics approaches to characterize the tumor and immunological landscape of 61 samples. We observed a spatial and HCC-recurrence-associated distribution of natural killer (NK) cells in the invasive front and tumor center. Using artificial-intelligence alongside an extreme gradient-boosting algorithm, we developed the Tumor Immune MicroEnvironment Spatial (“TIMES”) score based on the expression of five NK-associated markers (SPON2, ZFP36L2, ZFP36, VIM, and HLA-DRB1) to predict HCC recurrence. We also demonstrated that TIMES score (HR = 29.6, P \u003c 0.001) outperforms the current standard tools for patient risk stratification including the TNM (HR = 1.93, P = 0.113) and BCLC (HR = 1.55, P = 0.253) systems. In the clinic, we validated the model in 103 patients from three multi-centered cohorts achieve a real-world sensitivity of 90.00% and specificity of 90.24%. In the lab, following up on the individual marker with the highest prediction accuracy, in vivo models revealed that SPON2 increases IFN-γ secretion and enhances infiltration potential of NK cells at the invasive front. Additionally, we established the TIMES score on a publicly accessible website that can be easily achieved by different levels of pathology labs to facilitate global prediction of HCC recurrence risk and stratification of high-risk patients. With its ability to efficiently stratify high-risk patients, it exemplifying the utility of artificial intelligence to improve our understanding on TIME features that underlie tumor progression.","manuscriptTitle":"Early Identification of High-Risk Patients with HCC Relapse: A Spatial Immune Scoring System Enabled by Artificial Intelligence","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-04-03 02:51:30","doi":"10.21203/rs.3.rs-2707861/v1","editorialEvents":[],"status":"published","journal":{"display":false,"email":"[email protected]","identity":"nature","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"nature","sideBox":"Learn more about [Nature](http://www.nature.com/nature/)","snPcode":"","submissionUrl":"","title":"Nature","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"96f0e3ff-505c-4264-9217-76084e56d1b0","owner":[],"postedDate":"April 3rd, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":20398064,"name":"Health sciences/Diseases/Cancer/Cancer microenvironment"},{"id":20398065,"name":"Biological sciences/Immunology/Lymphocytes/NK cells"},{"id":20398066,"name":"Health sciences/Diseases/Cancer/Tumour immunology/Immunosurveillance"},{"id":20398067,"name":"Biological sciences/Cancer/Cancer prevention"}],"tags":[],"updatedAt":"2025-03-13T07:05:39+00:00","versionOfRecord":{"articleIdentity":"rs-2707861","link":"https://doi.org/10.1038/s41586-025-08668-x","journal":{"identity":"nature","isVorOnly":false,"title":"Nature"},"publishedOn":"2025-03-12 04:00:00","publishedOnDateReadable":"March 12th, 2025"},"versionCreatedAt":"2023-04-03 02:51:30","video":"","vorDoi":"10.1038/s41586-025-08668-x","vorDoiUrl":"https://doi.org/10.1038/s41586-025-08668-x","workflowStages":[]},"version":"v1","identity":"rs-2707861","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2707861","identity":"rs-2707861","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}