{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T05:54:33Z","timestamp":1791266073360,"version":"4.1.0"},"reference-count":60,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T00:00:00Z","timestamp":1791244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>\n                    Immune checkpoint inhibitor response in non-small cell lung cancer (NSCLC) reflects coordinated tumor and immune states that are not fully captured by single biomarkers. We developed scTIME, an interpretable model that translates single-cell immune programs into bulk transcriptomic scores, and integrated public single-cell, T-cell receptor, transcriptomic, survival, and proteogenomic cohorts. Response modeling used two cohorts with different endpoints (40 patients) and compared six algorithms. ElasticNet was selected as a sparse reporting model, achieving a pooled five-fold out-of-fold ROC-AUC of 0.810; nested model selection yielded 0.772. Matched held-out stratification identified response-enriched scTIME groups in a direct descriptive comparison with CD274, while the fitted score emphasized cytotoxic CD8, natural killer, SPP1 macrophage, interferon-response, and antigen-presentation programs. Single-cell analyses and external projections linked these programs to CXCL10-CXCR3 recruitment, exclusion-associated states, and T-cell receptor ecology across molecular contexts. Exploratory survival and cross-omics analyses extended the framework beyond the response cohorts but were interpreted as projection rather than independent validation. Together, the results show how cell-resolved immune biology can support transparent, multi-omic biomarker development without reducing response to a single pathway. scTIME remains exploratory because model choice was\n                    <jats:italic>post hoc<\/jats:italic>\n                    , cohorts were small and clinically heterogeneous, and endpoint-matched external validation was unavailable.\n                  <\/jats:p>","DOI":"10.3389\/frai.2026.1918104","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T05:21:54Z","timestamp":1791264114000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["scTIME: single-cell-informed interpretable modeling of immunotherapy-associated immune states in non-small cell lung cancer"],"prefix":"10.3389","volume":"9","author":[{"given":"Guozhi","family":"Chen","sequence":"first","affiliation":[{"name":"YongJia People's Hospital","place":["Wenzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenqiu","family":"You","sequence":"additional","affiliation":[{"name":"YongJia People's Hospital","place":["Wenzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanxi Acupuncture Hospital","place":["Taiyuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengjie","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,6]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","article-title":"Multimodal biomedical AI","volume":"28","author":"Acosta","year":"2022","journal-title":"Nat. Med."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s00262-025-04180-3","article-title":"Single-cell transcriptomic analyses provide insights into SPP1+ TAM-mediated immune suppression and CD8+ T cell dysfunction in lung cancer","volume":"74","author":"Almgrami","year":"2025","journal-title":"Cancer Immunol. Immunother."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"n2281","DOI":"10.1136\/bmj.n2281","article-title":"Risk of bias in studies on prediction models developed using supervised machine learning techniques: systematic review","volume":"375","author":"Andaur Navarro","year":"2021","journal-title":"BMJ"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"2482","DOI":"10.1038\/s41588-025-02351-7","article-title":"Spatial signatures for predicting immunotherapy outcomes using multi-omics in non-small cell lung cancer","volume":"57","author":"Aung","year":"2025","journal-title":"Nat. Genet."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"34580079","DOI":"10.1101\/cshperspect.a037895","article-title":"Tumor immunology and immunotherapy of non-small-cell lung Cancer","volume":"12","author":"Cascone","year":"2022","journal-title":"Cold Spring Harb. Perspect. Med."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1038\/s41586-021-03752-4","article-title":"Transcriptional programs of neoantigen-specific TIL in anti-PD-1-treated lung cancers","volume":"596","author":"Caushi","year":"2021","journal-title":"Nature"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/s00262-024-03761-y","article-title":"Tumor-intrinsic IFNalpha and CXCL10 are critical for immunotherapeutic efficacy by recruiting and activating T lymphocytes in tumor microenvironment","volume":"73","author":"Cheng","year":"2024","journal-title":"Cancer Immunol. Immunother."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1016\/j.ccell.2023.12.021","article-title":"Cancer-associated fibroblast phenotypes are associated with patient outcome in non-small cell lung cancer","volume":"42","author":"Cords","year":"2024","journal-title":"Cancer Cell"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1186\/s12943-025-02287-w","article-title":"Single-cell and spatial transcriptomic analyses revealing tumor microenvironment remodeling after neoadjuvant chemoimmunotherapy in non-small cell lung cancer","volume":"24","author":"Cui","year":"2025","journal-title":"Mol. Cancer"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"eadg1487","DOI":"10.1126\/sciimmunol.adg1487","article-title":"Lung tumor-infiltrating Treg have divergent transcriptional profiles and function linked to checkpoint blockade response","volume":"8","author":"Dykema","year":"2023","journal-title":"Sci. Immunol."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"CD013257","DOI":"10.1002\/14651858.CD013257.pub3","article-title":"Single or combined immune checkpoint inhibitors compared to first-line platinum-based chemotherapy with or without bevacizumab for people with advanced non-small cell lung cancer","volume":"4","author":"Ferrara","year":"2021","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1973","DOI":"10.1056\/NEJMoa2202170","article-title":"Neoadjuvant Nivolumab plus chemotherapy in Resectable lung Cancer","volume":"386","author":"Forde","year":"2022","journal-title":"N. Engl. J. Med."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"799455","DOI":"10.3389\/fimmu.2021.799455","article-title":"Therapeutic implications of tumor microenvironment in lung cancer: focus on immune checkpoint blockade","volume":"12","author":"Genova","year":"2021","journal-title":"Front. Immunol."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e745","DOI":"10.1016\/S2589-7500(21)00208-9","article-title":"The false hope of current approaches to explainable artificial intelligence in health care","volume":"3","author":"Ghassemi","year":"2021","journal-title":"Lancet Digit. Health"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2606","DOI":"10.1158\/2159-8290.CD-21-1714","article-title":"Spatial positioning and matrix programs of Cancer-associated fibroblasts promote T-cell exclusion in human lung tumors","volume":"12","author":"Grout","year":"2022","journal-title":"Cancer Discov."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1453232","DOI":"10.3389\/fimmu.2024.1453232","article-title":"Whole slide image-based weakly supervised deep learning for predicting major pathological response in non-small cell lung cancer following neoadjuvant chemoimmunotherapy: a multicenter, retrospective, cohort study","volume":"15","author":"Han","year":"2024","journal-title":"Front. Immunol."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"3573","DOI":"10.1016\/j.cell.2021.04.048","article-title":"Integrated analysis of multimodal single-cell data","volume":"184","author":"Hao","year":"2021","journal-title":"Cell"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1602452","DOI":"10.3389\/fonc.2025.1602452","article-title":"Role of TGFbeta-activated cancer-associated fibroblasts in the resistance to checkpoint blockade immunotherapy","volume":"15","author":"Hou","year":"2025","journal-title":"Front. Oncol."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s13073-023-01164-9","article-title":"Tumor microenvironment remodeling after neoadjuvant immunotherapy in non-small cell lung cancer revealed by single-cell RNA sequencing","volume":"15","author":"Hu","year":"2023","journal-title":"Genome Med."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"106988","DOI":"10.1016\/j.phrs.2023.106988","article-title":"Ginsenoside Rh2 augmented anti-PD-L1 immunotherapy by reinvigorating CD8+ T cells via increasing intratumoral CXCL10","volume":"198","author":"Huang","year":"2023","journal-title":"Pharmacol. Res."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"33597522","DOI":"10.1038\/s41467-021-21246-9","article-title":"Inference and analysis of cell-cell communication using CellChat","volume":"12","author":"Jin","year":"2021","journal-title":"Nat. Commun."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"4067","DOI":"10.1038\/s41467-024-48310-4","article-title":"Systematic dissection of tumor-normal single-cell ecosystems across a thousand tumors of 30 cancer types","volume":"15","author":"Kang","year":"2024","journal-title":"Nat. Commun."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e003890","DOI":"10.1136\/jitc-2021-003890","article-title":"Spatial transcriptomics of macrophage infiltration in non-small cell lung cancer reveals determinants of sensitivity and resistance to anti-PD1\/PD-L1 antibodies","volume":"10","author":"Larroquette","year":"2022","journal-title":"J. Immunother. Cancer"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1594","DOI":"10.1016\/j.ccell.2021.10.009","article-title":"Single-cell analysis of human non-small cell lung cancer lesions refines tumor classification and patient stratification","volume":"39","author":"Leader","year":"2021","journal-title":"Cancer Cell"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"3081","DOI":"10.1016\/j.cell.2025.03.018","article-title":"A single-cell atlas reveals immune heterogeneity in anti-PD-1-treated non-small cell lung cancer","volume":"188","author":"Liu","year":"2025","journal-title":"Cell"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"e2501791122","DOI":"10.1073\/pnas.2501791122","article-title":"Development of DPP-4-resistant CXCL9-fc and CXCL10-fc chemokines for effective cancer immunotherapy","volume":"122","author":"Lugassy","year":"2025","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1016\/j.ccell.2025.03.012","article-title":"Leveraging real-world data to advance biomarker discovery and precision oncology","volume":"43","author":"Luo","year":"2025","journal-title":"Cancer Cell"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"112129","DOI":"10.1016\/j.celrep.2023.112129","article-title":"TGF-beta in the microenvironment induces a physiologically occurring immune-suppressive senescent state","volume":"42","author":"Matsuda","year":"2023","journal-title":"Cell Rep."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.ccell.2023.12.013","article-title":"Clinical and molecular features of acquired resistance to immunotherapy in non-small cell lung cancer","volume":"42","author":"Memon","year":"2024","journal-title":"Cancer Cell"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/bs.mcb.2025.01.003","article-title":"Next-generation deconvolution of the tumor microenvironment with omnideconv","volume":"196","author":"Merotto","year":"2025","journal-title":"Methods Cell Biol."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"e082505","DOI":"10.1136\/bmj-2024-082505","article-title":"PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"Moons","year":"2025","journal-title":"BMJ"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"e1011365","DOI":"10.1371\/journal.pcbi.1011365","article-title":"Deconvolution of cancer cell states by the XDec-SM method","volume":"19","author":"Murillo","year":"2023","journal-title":"PLoS Comput. Biol."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.ccell.2022.02.002","article-title":"Intratumoral plasma cells predict outcomes to PD-L1 blockade in non-small cell lung cancer","volume":"40","author":"Patil","year":"2022","journal-title":"Cancer Cell"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"39273605","DOI":"10.3390\/ijms25179659","article-title":"Predictive biomarkers and resistance mechanisms of checkpoint inhibitors in malignant solid tumors","volume":"25","author":"Pavelescu","year":"2024","journal-title":"Int. J. Mol. Sci."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1493877","DOI":"10.3389\/fimmu.2024.1493877","article-title":"Biomarkers of success of anti-PD-(L)1 immunotherapy for non-small cell lung cancer derived from RNA- and whole-exome sequencing: results of a prospective observational study on a cohort of 85 patients","volume":"15","author":"Poddubskaya","year":"2024","journal-title":"Front. Immunol."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat. Med."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1001\/jamaoncol.2022.4933","article-title":"Association of machine learning-based assessment of tumor-infiltrating lymphocytes on standard histologic images with outcomes of immunotherapy in patients with NSCLC","volume":"9","author":"Rakaee","year":"2023","journal-title":"JAMA Oncol."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1001\/jamaoncol.2024.5356","article-title":"Deep learning model for predicting immunotherapy response in advanced non-small cell lung cancer","volume":"11","author":"Rakaee","year":"2025","journal-title":"JAMA Oncol."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1038\/s41588-023-01355-5","article-title":"Genomic and transcriptomic analysis of checkpoint blockade response in advanced non-small cell lung cancer","volume":"55","author":"Ravi","year":"2023","journal-title":"Nat. Genet."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1186\/s12943-024-02177-7","article-title":"Single-cell RNA sequencing reveals immune microenvironment niche transitions during the invasive and metastatic processes of ground-glass nodules and part-solid nodules in lung adenocarcinoma","volume":"23","author":"Ren","year":"2024","journal-title":"Mol. Cancer"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"e074820","DOI":"10.1136\/bmj-2023-074820","article-title":"Evaluation of clinical prediction models (part 2): how to undertake an external validation study","volume":"384","author":"Riley","year":"2024","journal-title":"BMJ"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"39585348","DOI":"10.1084\/jem.20231106","article-title":"Hypoxia is linked to acquired resistance to immune checkpoint inhibitors in lung cancer","volume":"222","author":"Robles-Oteiza","year":"2025","journal-title":"J. Exp. Med."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"e404","DOI":"10.1016\/S2589-7500(23)00082-1","article-title":"Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study","volume":"5","author":"Saad","year":"2023","journal-title":"Lancet Digit. Health"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"4348","DOI":"10.1016\/j.cell.2021.07.016","article-title":"A proteogenomic portrait of lung squamous cell carcinoma","volume":"184","author":"Satpathy","year":"2021","journal-title":"Cell"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"747","DOI":"10.7150\/thno.65828","article-title":"Nintedanib enhances the efficacy of PD-L1 blockade by upregulating MHC-I and PD-L1 expression in tumor cells","volume":"12","author":"Tu","year":"2022","journal-title":"Theranostics"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1158\/2326-6066.CIR-22-0283","article-title":"iBRIDGE: a data integration method to identify inflamed tumors from single-cell RNA-Seq data and differentiate cell type-specific markers of immune-cell infiltration","volume":"11","author":"Turan","year":"2023","journal-title":"Cancer Immunol. Res."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s00428-021-03030-8","article-title":"Predictive biomarkers for response to immune checkpoint inhibitors in lung cancer: PD-L1 and beyond","volume":"478","author":"Uruga","year":"2021","journal-title":"Virchows Arch."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s41512-023-00148-y","article-title":"Decision curve analysis: confidence intervals and hypothesis testing for net benefit","volume":"7","author":"Vickers","year":"2023","journal-title":"Diagn. Progn. Res."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"36921054","DOI":"10.1126\/sciadv.add8564","article-title":"Synthetic enforcement of STING signaling in cancer cells appropriates the immune microenvironment for checkpoint inhibitor therapy","volume":"9","author":"Vornholz","year":"2023","journal-title":"Sci. Adv."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1007\/s00262-023-03379-6","article-title":"Radiotherapy enhances CXCR3highCD8+ T cell activation through inducing IFNgamma-mediated CXCL10 and ICAM-1 expression in lung cancer cells","volume":"72","author":"Wang","year":"2023","journal-title":"Cancer Immunol. Immunother."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"2279800","DOI":"10.1080\/2162402X.2023.2279800","article-title":"Tumor-intrinsic RGS1 potentiates checkpoint blockade response via ATF3-IFNGR1 axis","volume":"12","author":"Wang","year":"2023","journal-title":"Onco Targets Ther"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1186\/s13046-025-03519-z","article-title":"Immunotherapy resistance in non-small cell lung cancer: from mechanisms to therapeutic opportunities","volume":"44","author":"Wang","year":"2025","journal-title":"J. Exp. Clin. Cancer Res."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s10555-022-10074-y","article-title":"Potential biomarkers for immunotherapy in non-small-cell lung cancer","volume":"42","author":"Wang","year":"2023","journal-title":"Cancer Metastasis Rev."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1038\/s41392-022-01130-8","article-title":"The heterogeneous immune landscape between lung adenocarcinoma and squamous carcinoma revealed by single-cell RNA sequencing","volume":"7","author":"Wang","year":"2022","journal-title":"Signal Transduct. Target. Ther."},{"key":"ref56","doi-asserted-by":"publisher","first-page":"1366260","DOI":"10.3389\/fimmu.2024.1366260","article-title":"Mechanisms of resistance to targeted therapy and immunotherapy in non-small cell lung cancer: promising strategies to overcoming challenges","volume":"15","author":"Xiang","year":"2024","journal-title":"Front. Immunol."},{"key":"ref57","doi-asserted-by":"publisher","first-page":"e2407096121","DOI":"10.1073\/pnas.2407096121","article-title":"DeSide: a unified deep learning approach for cellular deconvolution of tumor microenvironment","volume":"121","author":"Xiong","year":"2024","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref58","doi-asserted-by":"publisher","first-page":"1814","DOI":"10.1002\/ijc.35301","article-title":"Hypoxia-inducible factor-targeting therapy augmented the sensitivity to programmed death ligand-1 blockade by enhancing interferon-gamma-induced chemokines in tumor cells","volume":"156","author":"Yabuki","year":"2025","journal-title":"Int. J. Cancer"},{"key":"ref59","doi-asserted-by":"publisher","first-page":"e009348","DOI":"10.1136\/jitc-2024-009348","article-title":"Non-invasive multimodal CT deep learning biomarker to predict pathological complete response of non-small cell lung cancer following neoadjuvant immunochemotherapy: a multicenter study","volume":"12","author":"Ye","year":"2024","journal-title":"J. Immunother. Cancer"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"21","DOI":"10.20517\/cdr.2025.14","article-title":"Tumor microenvironment-driven resistance to immunotherapy in non-small cell lung cancer: strategies for cold-to-hot tumor transformation","volume":"8","author":"Yu","year":"2025","journal-title":"Cancer Drug Resist."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1918104\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T05:21:55Z","timestamp":1791264115000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1918104\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,6]]},"references-count":60,"alternative-id":["10.3389\/frai.2026.1918104"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1918104","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,6]]},"article-number":"1918104"}}