Deep Learning Paradigm for Precision Lung Cancer Therapy with AI-Driven Genotype-Phenotype Mining and Patient-Derived Organoid Validation

Deep Learning Paradigm for Precision Lung Cancer Therapy with AI-Driven Genotype-Phenotype Mining and Patient-Derived Organoid Validation | 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 Deep Learning Paradigm for Precision Lung Cancer Therapy with AI-Driven Genotype-Phenotype Mining and Patient-Derived Organoid Validation Zhongze Gu, Mingyue Li, Xiaoming Shi, Tianmu Hu, Juan Zhang, Ziliang Ye, and 13 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8251435/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 and accurate prediction of anticancer drug responses is critical for enhancing treatment efficacy and improving clinical outcomes in cancer patients. However, the practical implementation of current predictive models is hampered by dual limitations: machine learning approaches reliant on cell line data often exhibit suboptimal accuracy, while patient-derived organoids (PDOs) platform typically lack the rapid turnaround required for timely clinical decision-making. Here, we present a deep learning framework to predict drug response in lung cancer patients by integrating patient genomic sequencing data with compound structural information, trained against phenotypic drug sensitivity profiles from lung cancer PDOs, to predict drug responses in lung cancer patients. Our model enables individualized prediction of antitumor activity across diverse chemical structures, demonstrating capabilities for predicting efficacy of both approved drugs and novel compounds, as well as facilitating drug repurposing. The framework achieved 81.6% prediction accuracy, which was experimentally validated using patient-derived organoid models. More importantly, evaluation in a clinical cohort of lung cancer patients confirmed the model's ability to accurately reflect actual treatment responses. This study represents the first successful integration of genotype, drug structure, and organoid phenotype within a unified computational framework, significantly enhancing the accuracy and biological interpretability of drug response predictions while providing a clinically applicable tool for precision oncology in lung cancer. Biological sciences/Computational biology and bioinformatics/Machine learning Health sciences/Diseases/Cancer Full Text Additional Declarations There is NO Competing Interest. Statement of Ethics Approval: This research protocol was reviewed and approved by the Medical Ethics Committee of Nanjing Drum Tower Hospital, the Affiliated Hospital of Nanjing University Medical School (Approval No.: 2024-206-02). All procedures involving human participants were conducted in accordance with the ethical standards of the committee and the principles of the Declaration of Helsinki. Written informed consent was obtained from all participants (or their legal guardians, where applicable). Supplementary Files SupplementarytableS5Validationofdrugresponsefeatureinclinicaldata.xlsx Supplementary table S5 SupplementarytableS2.Compoundsandtheirtargetsfordeeplearningmodelconstruction.xlsx Supplementary table S2 Ethicalguidelinesandregulations.pdf Ethical guidelines and regulations SupplementarytableS3.AZD5363EGFRT790M.xlsx Supplementary table S3 SupplementarytableS1Pathologicalinformationofalltheresectedsamples.xlsx Supplementary table S1 SupplementarytableS4.IntegratedComputationalExperimentalValidationofDeepLearningModel.xlsx Supplementary table S4 Supportinginformation20251201.docx Supporting information Theinstitutionsethicalguidelinesandregulations.pdf Institution's ethical guidelines and regulations commsjGu.pdf Communications Journals Checklist Supportinginformation20251211.docx Supplementary Information Revised RSGuWangXuChen.pdf Reporting Summary 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-8251435","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":561823490,"identity":"0dd45f29-312d-444d-80f7-bda2071903e8","order_by":0,"name":"Zhongze Gu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAoklEQVRIiWNgGAWjYFAC5gMQ+gDxWtgSSNbCY0CiFvmInM8fPrYxyPHdSGD8XECMFsMbudskZ7YxGEveSGCWnkGUlhm525h52xgSN9xIYGPmIU5LzuPPf9sY6onXIi+RwyDN2MaQYEC0FgOeZ2aSPeckDGeeedgsTZwt7cmPP/wos5HnO5588DNxthwAUxJAzNhAjAagLUSqGwWjYBSMgpEMADo6Lx66euroAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-8926-7710","institution":"Southeast University","correspondingAuthor":true,"prefix":"","firstName":"Zhongze","middleName":"","lastName":"Gu","suffix":""},{"id":561823491,"identity":"a4a1d62e-3b57-4ef6-b17c-7aaa6e138c5f","order_by":1,"name":"Mingyue Li","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Mingyue","middleName":"","lastName":"Li","suffix":""},{"id":561823492,"identity":"163f1c6f-2ced-4fef-99bc-cda1a55d8cfd","order_by":2,"name":"Xiaoming Shi","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital","correspondingAuthor":false,"prefix":"","firstName":"Xiaoming","middleName":"","lastName":"Shi","suffix":""},{"id":561823493,"identity":"af43ff6e-b0b6-439c-89de-9c8195f53821","order_by":3,"name":"Tianmu Hu","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Tianmu","middleName":"","lastName":"Hu","suffix":""},{"id":561823494,"identity":"0c8487a2-49fb-4af3-b7e7-61f0573e4b1c","order_by":4,"name":"Juan Zhang","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Juan","middleName":"","lastName":"Zhang","suffix":""},{"id":561823495,"identity":"a51474de-8366-4f8a-a09b-92f94f2fceba","order_by":5,"name":"Ziliang Ye","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Ziliang","middleName":"","lastName":"Ye","suffix":""},{"id":561823496,"identity":"68917029-9c87-4930-a498-157c7c844397","order_by":6,"name":"Yuhan Cai","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Yuhan","middleName":"","lastName":"Cai","suffix":""},{"id":561823497,"identity":"c32851cb-2119-4f1b-ba32-914399605b75","order_by":7,"name":"Qiwei Li","email":"","orcid":"","institution":"China Jiliang University","correspondingAuthor":false,"prefix":"","firstName":"Qiwei","middleName":"","lastName":"Li","suffix":""},{"id":561823498,"identity":"d1c89046-1459-4887-902b-a9d506dd4b3d","order_by":8,"name":"Linchong Liu","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital","correspondingAuthor":false,"prefix":"","firstName":"Linchong","middleName":"","lastName":"Liu","suffix":""},{"id":561823499,"identity":"5161df53-317e-4d83-b98e-fe0171e6cb33","order_by":9,"name":"Wenlong Yu","email":"","orcid":"","institution":"Jiangsu Institute for Sport and Health","correspondingAuthor":false,"prefix":"","firstName":"Wenlong","middleName":"","lastName":"Yu","suffix":""},{"id":561823500,"identity":"8254f9d3-97f8-44cc-a3b1-9ea49f730dda","order_by":10,"name":"Jiajia Jing","email":"","orcid":"","institution":"Jiangsu Institute for Sport and Health","correspondingAuthor":false,"prefix":"","firstName":"Jiajia","middleName":"","lastName":"Jing","suffix":""},{"id":561823501,"identity":"940c39d5-8fc1-4b24-adf2-7a0d3381b682","order_by":11,"name":"Qiuyin Zhang","email":"","orcid":"","institution":"Jiangsu Institute for Sport and Health","correspondingAuthor":false,"prefix":"","firstName":"Qiuyin","middleName":"","lastName":"Zhang","suffix":""},{"id":561823502,"identity":"97347f4b-b207-4a84-a60c-e39ea3faaac8","order_by":12,"name":"Juanjuan Li","email":"","orcid":"","institution":"Jiangsu Avatarget Biotechnology","correspondingAuthor":false,"prefix":"","firstName":"Juanjuan","middleName":"","lastName":"Li","suffix":""},{"id":561823503,"identity":"e22bfe53-7dab-44e4-8c22-2274c439576b","order_by":13,"name":"Xin Zhou","email":"","orcid":"https://orcid.org/0009-0005-2535-4846","institution":"Chinese Academy Of Agricultural Sciences","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Zhou","suffix":""},{"id":561823504,"identity":"4746640f-ce03-481a-9044-862b9bccb417","order_by":14,"name":"Nan Qiao","email":"","orcid":"","institution":"Huawei Cloud Computing Technologies Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Nan","middleName":"","lastName":"Qiao","suffix":""},{"id":561823505,"identity":"2207482b-a184-454f-a8c0-6c27f6164313","order_by":15,"name":"Jun Bao","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Bao","suffix":""},{"id":561823506,"identity":"d6b9cb2c-221d-490e-93a7-6526ee7645e3","order_by":16,"name":"Zaozao Chen","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Zaozao","middleName":"","lastName":"Chen","suffix":""},{"id":561823507,"identity":"47acaf95-d987-49ee-954e-59ccbfcbb4b6","order_by":17,"name":"Lili Xu","email":"","orcid":"","institution":"China Pharmaceutical University","correspondingAuthor":false,"prefix":"","firstName":"Lili","middleName":"","lastName":"Xu","suffix":""},{"id":561823508,"identity":"238fc784-f4d3-4bd2-a651-aa0d6f868432","order_by":18,"name":"Tao Wang","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-12-01 14:26:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8251435/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8251435/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101202982,"identity":"815d773f-cb95-41c5-aa13-6c59e8931f05","added_by":"auto","created_at":"2026-01-27 09:38:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1816762,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript20251211EditedforRevision31.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1_covered_13b08166-a4e9-45aa-b13e-3bf224de26c2.pdf"},{"id":98892331,"identity":"c7835ce6-0f28-4bd5-8ee3-e581d92dd78d","added_by":"auto","created_at":"2025-12-23 16:32:34","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":12737,"visible":true,"origin":"","legend":"Supplementary table S5","description":"","filename":"SupplementarytableS5Validationofdrugresponsefeatureinclinicaldata.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/a12a735b309c07b7fdf014e6.xlsx"},{"id":98892332,"identity":"243ade75-1f35-4511-a369-8b12264ed6ba","added_by":"auto","created_at":"2025-12-23 16:32:34","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":13787,"visible":true,"origin":"","legend":"Supplementary table S2","description":"","filename":"SupplementarytableS2.Compoundsandtheirtargetsfordeeplearningmodelconstruction.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/728bfd2e2ec6c12d7710a8a2.xlsx"},{"id":98892334,"identity":"cd5c0323-1f7d-47e3-9bbb-cc415933a7b5","added_by":"auto","created_at":"2025-12-23 16:32:34","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":1000201,"visible":true,"origin":"","legend":"Ethical guidelines and regulations","description":"","filename":"Ethicalguidelinesandregulations.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/0bfbb4ace7f7d11e354195e4.pdf"},{"id":99309272,"identity":"f7aa8990-7bd3-4be5-89f4-dcfa057316f1","added_by":"auto","created_at":"2025-12-31 16:09:58","extension":"xlsx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":1160431,"visible":true,"origin":"","legend":"Supplementary table S3","description":"","filename":"SupplementarytableS3.AZD5363EGFRT790M.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/7ba590e175d55473bbbce996.xlsx"},{"id":98892336,"identity":"f331fca8-6c78-4302-9e7e-9d58f1265c39","added_by":"auto","created_at":"2025-12-23 16:32:34","extension":"xlsx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":17820,"visible":true,"origin":"","legend":"Supplementary table S1","description":"","filename":"SupplementarytableS1Pathologicalinformationofalltheresectedsamples.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/adc11979767862098836a985.xlsx"},{"id":98892333,"identity":"096200bf-7ade-47b3-b107-2408f8931b54","added_by":"auto","created_at":"2025-12-23 16:32:34","extension":"xlsx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":15201,"visible":true,"origin":"","legend":"Supplementary table S4","description":"","filename":"SupplementarytableS4.IntegratedComputationalExperimentalValidationofDeepLearningModel.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/914acff9ee26e593bac01d36.xlsx"},{"id":98892338,"identity":"1becd7f2-3e2c-4d0c-bf3a-a5b310ba4606","added_by":"auto","created_at":"2025-12-23 16:32:34","extension":"docx","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":4434101,"visible":true,"origin":"","legend":"Supporting information","description":"","filename":"Supportinginformation20251201.docx","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/de0e9e433847afa2551e2f34.docx"},{"id":99309736,"identity":"112bdc0c-31c4-4b83-bd58-13d92b801cd1","added_by":"auto","created_at":"2025-12-31 16:11:02","extension":"pdf","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":1030098,"visible":true,"origin":"","legend":"Institution's ethical guidelines and regulations","description":"","filename":"Theinstitutionsethicalguidelinesandregulations.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/df9853623ae1261c6dc2b4b4.pdf"},{"id":98892339,"identity":"d2086b62-012e-4c86-ab03-7d53fe946cd9","added_by":"auto","created_at":"2025-12-23 16:32:34","extension":"pdf","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":2353931,"visible":true,"origin":"","legend":"Communications Journals Checklist","description":"","filename":"commsjGu.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/cdc84e9a22528cb258352be3.pdf"},{"id":98892340,"identity":"1812fb21-8c7b-481b-92a9-5d697de26124","added_by":"auto","created_at":"2025-12-23 16:32:34","extension":"docx","order_by":10,"title":"","display":"","copyAsset":false,"role":"supplement","size":4434110,"visible":true,"origin":"","legend":"Supplementary Information Revised","description":"","filename":"Supportinginformation20251211.docx","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/185b40c8c7ebb197b0776e6c.docx"},{"id":98892341,"identity":"3518d488-7a44-456d-adc9-a4acb5951afa","added_by":"auto","created_at":"2025-12-23 16:32:34","extension":"pdf","order_by":11,"title":"","display":"","copyAsset":false,"role":"supplement","size":5335710,"visible":true,"origin":"","legend":"Reporting Summary","description":"","filename":"RSGuWangXuChen.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8251435/v1/15bb644516cc0e83f79793bf.pdf"}],"financialInterests":"\u003cp\u003eThere is \u003cstrong\u003eNO\u003c/strong\u003e Competing Interest.\u003c/p\u003e\n\u003cp\u003eStatement of Ethics Approval: This research protocol was reviewed and approved by the Medical Ethics Committee of Nanjing Drum Tower Hospital, the Affiliated Hospital of Nanjing University Medical School (Approval No.: 2024-206-02). All procedures involving human participants were conducted in accordance with the ethical standards of the committee and the principles of the Declaration of Helsinki. Written informed consent was obtained from all participants (or their legal guardians, where applicable).\u003c/p\u003e","formattedTitle":"Deep Learning Paradigm for Precision Lung Cancer Therapy with AI-Driven Genotype-Phenotype Mining and Patient-Derived Organoid Validation","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-8251435/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8251435/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The rapid and accurate prediction of anticancer drug responses is critical for enhancing treatment efficacy and improving clinical outcomes in cancer patients. However, the practical implementation of current predictive models is hampered by dual limitations: machine learning approaches reliant on cell line data often exhibit suboptimal accuracy, while patient-derived organoids (PDOs) platform typically lack the rapid turnaround required for timely clinical decision-making. Here, we present a deep learning framework to predict drug response in lung cancer patients by integrating patient genomic sequencing data with compound structural information, trained against phenotypic drug sensitivity profiles from lung cancer PDOs, to predict drug responses in lung cancer patients. Our model enables individualized prediction of antitumor activity across diverse chemical structures, demonstrating capabilities for predicting efficacy of both approved drugs and novel compounds, as well as facilitating drug repurposing. The framework achieved 81.6% prediction accuracy, which was experimentally validated using patient-derived organoid models. More importantly, evaluation in a clinical cohort of lung cancer patients confirmed the model's ability to accurately reflect actual treatment responses. This study represents the first successful integration of genotype, drug structure, and organoid phenotype within a unified computational framework, significantly enhancing the accuracy and biological interpretability of drug response predictions while providing a clinically applicable tool for precision oncology in lung cancer.","manuscriptTitle":"Deep Learning Paradigm for Precision Lung Cancer Therapy with AI-Driven Genotype-Phenotype Mining and Patient-Derived Organoid Validation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-23 16:32:29","doi":"10.21203/rs.3.rs-8251435/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":"38c32ca9-6987-401a-b319-f7f2b5a0fec6","owner":[],"postedDate":"December 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":59824975,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":59824976,"name":"Health sciences/Diseases/Cancer"}],"tags":[],"updatedAt":"2026-01-23T11:30:43+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-23 16:32:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8251435","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8251435","identity":"rs-8251435","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}