{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T19:52:24Z","timestamp":1787687544293,"version":"build-2784847793"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000072","name":"U.S. Department of Health & Human Services | NIH | National Institute of Dental and Craniofacial Research","doi-asserted-by":"publisher","award":["R01DE030894"],"award-info":[{"award-number":["R01DE030894"]}],"id":[{"id":"10.13039\/100000072","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Med"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Spatial proteomics enables high-resolution mapping of protein expression and can transform our understanding of biology and disease. However, major challenges remain for clinical translation, including cost, complexity and scalability. Here we present H&amp;E to protein expression (HEX), an AI model designed to computationally generate spatial proteomics profiles from standard histopathology slides. Trained and validated on 819,000 histopathology image tiles with matched protein expression from 382 tumor samples, HEX accurately predicts the expression of 40 biomarkers encompassing immune, structural and functional programs. HEX demonstrates substantial performance gains over alternative methods for protein expression prediction from H&amp;E images. We develop a multimodal data integration approach that combines the original H&amp;E image and AI-derived virtual spatial proteomics to enhance outcome prediction. Applied to six independent non-small-cell lung cancer cohorts totaling 2,298 patients, HEX-enabled multimodal integration improved prognostic accuracy by 22% and immunotherapy response prediction by 24\u201339% compared with conventional clinicopathological and molecular biomarkers. Biological interpretation revealed spatially organized tumor\u2013immune niches predictive of therapeutic response, including the co-localization of T helper cells and cytotoxic T cells in responders, and immunosuppressive tumor-associated macrophage and neutrophil aggregates in non-responders. HEX provides a low-cost and scalable approach to study spatial biology and enables the discovery and clinical translation of interpretable biomarkers for precision medicine.<\/jats:p>","DOI":"10.1038\/s41591-025-04060-4","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T10:02:02Z","timestamp":1767607322000},"page":"231-244","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["AI-enabled virtual spatial proteomics from histopathology for interpretable biomarker discovery in lung cancer"],"prefix":"10.1038","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0105-6351","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5476-3690","authenticated-orcid":false,"given":"Jinxi","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3597-9090","authenticated-orcid":false,"given":"Xiyue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0639-4122","authenticated-orcid":false,"given":"Sen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feyisope","family":"Eweje","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8574-0005","authenticated-orcid":false,"given":"Xiangde","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5666-9403","authenticated-orcid":false,"given":"Jonathan","family":"Mulholland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3271-0915","authenticated-orcid":false,"given":"Colin","family":"Bergstrom","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ted","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesca Maria","family":"Olguin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sierra","family":"Willens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6857-341X","authenticated-orcid":false,"given":"Jeffrey J.","family":"Nirschl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"West","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3119-9334","authenticated-orcid":false,"given":"Joel","family":"Neal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2032-0581","authenticated-orcid":false,"given":"Maximilian","family":"Diehn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0232-5998","authenticated-orcid":false,"given":"Ruijiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"key":"4060_CR1","doi-asserted-by":"crossref","first-page":"eabq4964","DOI":"10.1126\/science.abq4964","volume":"381","author":"D Bressan","year":"2023","unstructured":"Bressan, D., Battistoni, G. & Hannon, G. J. The dawn of spatial omics. Science 381, eabq4964 (2023).","journal-title":"Science"},{"key":"4060_CR2","doi-asserted-by":"crossref","first-page":"1653","DOI":"10.1016\/j.ccell.2024.09.001","volume":"42","author":"D Gong","year":"2024","unstructured":"Gong, D., Arbesfeld-Qiu, J. M., Perrault, E., Bae, J. W. & Hwang, W. L. Spatial oncology: translating contextual biology to the clinic. Cancer Cell 42, 1653\u20131675 (2024).","journal-title":"Cancer Cell"},{"key":"4060_CR3","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1038\/s41571-024-00926-7","volume":"21","author":"J Chen","year":"2024","unstructured":"Chen, J., Larsson, L., Swarbrick, A. & Lundeberg, J. Spatial landscapes of cancers: insights and opportunities. Nat. Rev. Clin. Oncol. 21, 660\u2013674 (2024).","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"4060_CR4","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1038\/s41580-024-00768-2","volume":"26","author":"GS Gulati","year":"2025","unstructured":"Gulati, G. S., D\u2019Silva, J. P., Liu, Y., Wang, L. & Newman, A. M. Profiling cell identity and tissue architecture with single-cell and spatial transcriptomics. Nat. Rev. Mol. Cell Biol. 26, 11\u201331 (2025).","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"4060_CR5","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.1038\/s41586-024-07793-3","volume":"632","author":"Y Harnik","year":"2024","unstructured":"Harnik, Y. et al. A spatial expression atlas of the adult human proximal small intestine. Nature 632, 1101\u20131109 (2024).","journal-title":"Nature"},{"key":"4060_CR6","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1038\/s41586-024-08061-0","volume":"635","author":"TM Nordmann","year":"2024","unstructured":"Nordmann, T. M. et al. Spatial proteomics identifies JAKi as treatment for a lethal skin disease. Nature 635, 1001\u20131009 (2024).","journal-title":"Nature"},{"key":"4060_CR7","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1038\/s41586-023-07011-6","volume":"627","author":"W Sun","year":"2024","unstructured":"Sun, W. et al. Spatial transcriptomics reveal neuron\u2013astrocyte synergy in long-term memory. Nature 627, 374\u2013381 (2024).","journal-title":"Nature"},{"key":"4060_CR8","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1038\/s41586-024-07944-6","volume":"635","author":"N Yayon","year":"2024","unstructured":"Yayon, N. et al. A spatial human thymus cell atlas mapped to a continuous tissue axis. Nature 635, 708\u2013718 (2024).","journal-title":"Nature"},{"key":"4060_CR9","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1038\/s41586-025-08668-x","volume":"640","author":"G Jia","year":"2025","unstructured":"Jia, G. et al. Spatial immune scoring system predicts hepatocellular carcinoma recurrence. Nature 640, 1031\u20131041 (2025).","journal-title":"Nature"},{"key":"4060_CR10","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1016\/j.ccell.2023.01.010","volume":"41","author":"O Elhanani","year":"2023","unstructured":"Elhanani, O., Ben-Uri, R. & Keren, L. Spatial profiling technologies illuminate the tumor microenvironment. Cancer Cell 41, 404\u2013420 (2023).","journal-title":"Cancer Cell"},{"key":"4060_CR11","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1016\/j.cell.2020.07.005","volume":"182","author":"CM Sch\u00fcrch","year":"2020","unstructured":"Sch\u00fcrch, C. M. et al. Coordinated cellular neighborhoods orchestrate antitumoral immunity at the colorectal cancer invasive front. Cell 182, 1341\u20131359.e19 (2020).","journal-title":"Cell"},{"key":"4060_CR12","doi-asserted-by":"crossref","first-page":"1559","DOI":"10.1038\/s41591-018-0177-5","volume":"24","author":"N Coudray","year":"2018","unstructured":"Coudray, N. et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat. Med. 24, 1559\u20131567 (2018).","journal-title":"Nat. Med."},{"key":"4060_CR13","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1038\/s43018-020-0085-8","volume":"1","author":"Y Fu","year":"2020","unstructured":"Fu, Y. et al. Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. Nat. Cancer 1, 800\u2013810 (2020).","journal-title":"Nat. Cancer"},{"key":"4060_CR14","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-024-54182-5","volume":"15","author":"M Pizurica","year":"2024","unstructured":"Pizurica, M. et al. Digital profiling of gene expression from histology images with linearized attention. Nat. Commun. 15, 9886 (2024).","journal-title":"Nat. Commun."},{"key":"4060_CR15","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1038\/s43018-020-0087-6","volume":"1","author":"JN Kather","year":"2020","unstructured":"Kather, J. N. et al. Pan-cancer image-based detection of clinically actionable genetic alterations. Nat. Cancer 1, 789\u2013799 (2020).","journal-title":"Nat. Cancer"},{"key":"4060_CR16","doi-asserted-by":"crossref","first-page":"e763","DOI":"10.1016\/S2589-7500(21)00180-1","volume":"3","author":"M Bilal","year":"2021","unstructured":"Bilal, M. et al. Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study. Lancet Digit. Health 3, e763\u2013e772 (2021).","journal-title":"Lancet Digit. Health"},{"key":"4060_CR17","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-020-17678-4","volume":"11","author":"B Schmauch","year":"2020","unstructured":"Schmauch, B. et al. A deep learning model to predict RNA-seq expression of tumours from whole slide images. Nat. Commun. 11, 3877 (2020).","journal-title":"Nat. Commun."},{"key":"4060_CR18","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1038\/s42256-024-00889-5","volume":"6","author":"P Pati","year":"2024","unstructured":"Pati, P. et al. Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling. Nat. Mach. Intell. 6, 1077\u20131093 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"4060_CR19","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-025-57717-6","volume":"16","author":"J Jasti","year":"2025","unstructured":"Jasti, J. et al. Histopathology based AI model predicts anti-angiogenic therapy response in renal cancer clinical trial. Nat. Commun. 16, 2610 (2025).","journal-title":"Nat. Commun."},{"key":"4060_CR20","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1038\/s42256-022-00471-x","volume":"4","author":"P Ghahremani","year":"2022","unstructured":"Ghahremani, P. et al. Deep learning-inferred multiplex immunofluorescence for immunohistochemical image quantification. Nat. Mach. Intell. 4, 401\u2013412 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"4060_CR21","doi-asserted-by":"crossref","first-page":"10528","DOI":"10.1016\/j.ebiom.2024.105287","volume":"107","author":"Z Zhou","year":"2024","unstructured":"Zhou, Z. et al. Virtual multiplexed immunofluorescence staining from non-antibody-stained fluorescence imaging for gastric cancer prognosis. eBioMedicine 107, 10528 (2024).","journal-title":"eBioMedicine"},{"key":"4060_CR22","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1038\/s41586-024-08378-w","volume":"638","author":"J Xiang","year":"2025","unstructured":"Xiang, J. et al. A vision\u2013language foundation model for precision oncology. Nature 638, 769\u2013778 (2025).","journal-title":"Nature"},{"key":"4060_CR23","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","volume":"30","author":"E Vorontsov","year":"2024","unstructured":"Vorontsov, E. et al. A foundation model for clinical-grade computational pathology and rare cancers detection. Nat. Med. 30, 2924\u20132935 (2024).","journal-title":"Nat. Med."},{"key":"4060_CR24","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","volume":"30","author":"MY Lu","year":"2024","unstructured":"Lu, M. Y. et al. A visual-language foundation model for computational pathology. Nat. Med. 30, 863\u2013874 (2024).","journal-title":"Nat. Med."},{"key":"4060_CR25","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","volume":"30","author":"RJ Chen","year":"2024","unstructured":"Chen, R. J. et al. Towards a general-purpose foundation model for computational pathology. Nat. Med. 30, 850\u2013862 (2024).","journal-title":"Nat. Med."},{"key":"4060_CR26","doi-asserted-by":"crossref","first-page":"1488","DOI":"10.1109\/TIP.2011.2173206","volume":"21","author":"D Brunet","year":"2012","unstructured":"Brunet, D., Vrscay, E. R. & Wang, Z. On the mathematical properties of the structural similarity index. IEEE Trans. Image Process. 21, 1488\u20131499 (2012).","journal-title":"IEEE Trans. Image Process."},{"key":"4060_CR27","doi-asserted-by":"crossref","first-page":"3042","DOI":"10.1109\/TMI.2020.2986331","volume":"39","author":"J Borovec","year":"2020","unstructured":"Borovec, J. et al. ANHIR: automatic non-rigid histological image registration challenge. IEEE Trans. Med. Imaging 39, 3042\u20133052 (2020).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"4060_CR28","doi-asserted-by":"publisher","unstructured":"Data from the National Lung Screening Trial (NLST). TCIA https:\/\/doi.org\/10.7937\/TCIA.HMQ8-J677 (2013).","DOI":"10.7937\/TCIA.HMQ8-J677"},{"key":"4060_CR29","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1001\/jama.2011.766","volume":"305","author":"SS Buys","year":"2011","unstructured":"Buys, S. S. et al. Effect of screening on ovarian cancer mortality: the prostate, lung, colorectal and ovarian (PLCO) cancer screening randomized controlled trial. J. Am. Med. Assoc. 305, 2295\u20132303 (2011).","journal-title":"J. Am. Med. Assoc."},{"key":"4060_CR30","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1016\/j.ccell.2022.07.004","volume":"40","author":"RJ Chen","year":"2022","unstructured":"Chen, R. J. et al. Pan-cancer integrative histology\u2013genomic analysis via multimodal deep learning. Cancer Cell 40, 865\u2013878.e6 (2022).","journal-title":"Cancer Cell"},{"key":"4060_CR31","unstructured":"Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In Proc. International Conference on Machine Learning 3319\u20133328 (PMLR, 2017)."},{"key":"4060_CR32","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1016\/j.immuni.2023.09.005","volume":"56","author":"JR Giles","year":"2023","unstructured":"Giles, J. R., Globig, A.-M., Kaech, S. M. & Wherry, E. J. CD8+ T cells in the cancer\u2013immunity cycle. Immunity 56, 2231\u20132253 (2023).","journal-title":"Immunity"},{"key":"4060_CR33","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1038\/s41586-023-06217-y","volume":"619","author":"M Damo","year":"2023","unstructured":"Damo, M. et al. PD-1 maintains CD8 T cell tolerance towards cutaneous neoantigens. Nature 619, 151\u2013159 (2023).","journal-title":"Nature"},{"key":"4060_CR34","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1016\/j.immuni.2019.03.009","volume":"50","author":"R Zilionis","year":"2019","unstructured":"Zilionis, R. et al. Single-cell transcriptomics of human and mouse lung cancers reveals conserved myeloid populations across individuals and species. Immunity 50, 1317\u20131334.e10 (2019).","journal-title":"Immunity"},{"key":"4060_CR35","volume":"13","author":"Y Lu","year":"2022","unstructured":"Lu, Y. et al. A single-cell atlas of the multicellular ecosystem of primary and metastatic hepatocellular carcinoma. Nat. Commun. 13, 4594 (2022).","journal-title":"Nat. Commun."},{"key":"4060_CR36","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1038\/s41590-023-01682-z","volume":"25","author":"D Zou","year":"2024","unstructured":"Zou, D. et al. CD4+ T cell immunity is dependent on an intrinsic stem-like program. Nat. Immunol. 25, 66\u201376 (2024).","journal-title":"Nat. Immunol."},{"key":"4060_CR37","volume":"22","author":"H Zhang","year":"2023","unstructured":"Zhang, H. et al. Define cancer-associated fibroblasts (CAFs) in the tumor microenvironment: new opportunities in cancer immunotherapy and advances in clinical trials. Mol. Cancer 22, 159 (2023).","journal-title":"Mol. Cancer"},{"key":"4060_CR38","first-page":"70626","volume":"36","author":"R Xie","year":"2023","unstructured":"Xie, R. et al. Spatially resolved gene expression prediction from histology images via bi-modal contrastive learning. Adv. Neural Inf. Process. Syst. 36, 70626\u201370637 (2023).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"4060_CR39","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1038\/s41592-025-02707-1","volume":"22","author":"W Chen","year":"2025","unstructured":"Chen, W. et al. A visual-omics foundation model to bridge histopathology with spatial transcriptomics. Nat. Methods 22, 1568\u20131582 (2025).","journal-title":"Nat. Methods"},{"key":"4060_CR40","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1038\/s41591-022-02134-1","volume":"29","author":"S Foersch","year":"2023","unstructured":"Foersch, S. et al. Multistain deep learning for prediction of prognosis and therapy response in colorectal cancer. Nat. Med. 29, 430\u2013439 (2023).","journal-title":"Nat. Med."},{"key":"4060_CR41","doi-asserted-by":"crossref","first-page":"1036","DOI":"10.1038\/s43018-023-00576-1","volume":"4","author":"J-R Lin","year":"2023","unstructured":"Lin, J.-R. et al. High-plex immunofluorescence imaging and traditional histology of the same tissue section for discovering image-based biomarkers. Nat. Cancer 4, 1036\u20131052 (2023).","journal-title":"Nat. Cancer"},{"key":"4060_CR42","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-021-26974-6","volume":"12","author":"D Phillips","year":"2021","unstructured":"Phillips, D. et al. Immune cell topography predicts response to PD-1 blockade in cutaneous T cell lymphoma. Nat. Commun. 12, 6726 (2021).","journal-title":"Nat. Commun."},{"key":"4060_CR43","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.ccell.2025.01.012","volume":"43","author":"H Chen","year":"2025","unstructured":"Chen, H. et al. Integrative spatial analysis reveals tumor heterogeneity and immune colony niche related to clinical outcomes in small cell lung cancer. Cancer Cell 43, 519\u2013536.e5 (2025).","journal-title":"Cancer Cell"},{"key":"4060_CR44","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1016\/j.ccell.2025.03.006","volume":"43","author":"SL Wang","year":"2025","unstructured":"Wang, S. L. & Chan, T. A. Navigating established and emerging biomarkers for immune checkpoint inhibitor therapy. Cancer Cell 43, 641\u2013664 (2025).","journal-title":"Cancer Cell"},{"key":"4060_CR45","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/S1470-2045(20)30641-0","volume":"22","author":"L Paz-Ares","year":"2021","unstructured":"Paz-Ares, L. et al. First-line nivolumab plus ipilimumab combined with two cycles of chemotherapy in patients with non-small-cell lung cancer (CheckMate 9LA): an international, randomised, open-label, phase 3 trial. Lancet Oncol. 22, 198\u2013211 (2021).","journal-title":"Lancet Oncol."},{"key":"4060_CR46","doi-asserted-by":"crossref","first-page":"4336","DOI":"10.1016\/j.cell.2024.07.018","volume":"187","author":"SF Ngiow","year":"2024","unstructured":"Ngiow, S. F. et al. LAG-3 sustains TOX expression and regulates the CD94\/NKG2\u2013Qa-1b axis to govern exhausted CD8 T cell NK receptor expression and cytotoxicity. Cell 187, 4336\u20134354.e19 (2024).","journal-title":"Cell"},{"key":"4060_CR47","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1038\/s41590-019-0312-6","volume":"20","author":"BC Miller","year":"2019","unstructured":"Miller, B. C. et al. Subsets of exhausted CD8+ T cells differentially mediate tumor control and respond to checkpoint blockade. Nat. Immunol. 20, 326\u2013336 (2019).","journal-title":"Nat. Immunol."},{"key":"4060_CR48","doi-asserted-by":"crossref","first-page":"20262","DOI":"10.1073\/pnas.0706438104","volume":"104","author":"VC Ardi","year":"2007","unstructured":"Ardi, V. C., Kupriyanova, T. A., Deryugina, E. I. & Quigley, J. P. Human neutrophils uniquely release TIMP-free MMP-9 to provide a potent catalytic stimulator of angiogenesis. Proc. Natl Acad. Sci. USA 104, 20262\u201320267 (2007).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"4060_CR49","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1136\/thoraxjnl-2016-209389","volume":"72","author":"A Vannitamby","year":"2017","unstructured":"Vannitamby, A. et al. Tumour-associated neutrophils and loss of epithelial PTEN can promote corticosteroid-insensitive MMP-9 expression in the chronically inflamed lung microenvironment. Thorax 72, 1140\u20131143 (2017).","journal-title":"Thorax"},{"key":"4060_CR50","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/S0092-8674(00)00139-2","volume":"103","author":"LM Coussens","year":"2000","unstructured":"Coussens, L. M., Tinkle, C. L., Hanahan, D. & Werb, Z. MMP-9 supplied by bone marrow-derived cells contributes to skin carcinogenesis. Cell 103, 481\u2013490 (2000).","journal-title":"Cell"},{"key":"4060_CR51","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s41586-022-05400-x","volume":"612","author":"R Xue","year":"2022","unstructured":"Xue, R. et al. Liver tumour immune microenvironment subtypes and neutrophil heterogeneity. Nature 612, 141\u2013147 (2022).","journal-title":"Nature"},{"key":"4060_CR52","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1038\/s41573-022-00520-5","volume":"21","author":"A Mantovani","year":"2022","unstructured":"Mantovani, A., Allavena, P., Marchesi, F. & Garlanda, C. Macrophages as tools and targets in cancer therapy. Nat. Rev. Drug Discov. 21, 799\u2013820 (2022).","journal-title":"Nat. Rev. Drug Discov."},{"key":"4060_CR53","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1038\/s41551-020-0578-x","volume":"4","author":"B He","year":"2020","unstructured":"He, B. et al. Integrating spatial gene expression and breast tumour morphology via deep learning. Nat. Biomed. Eng. 4, 827\u2013834 (2020).","journal-title":"Nat. Biomed. Eng."},{"key":"4060_CR54","doi-asserted-by":"crossref","first-page":"bbac297","DOI":"10.1093\/bib\/bbac297","volume":"23","author":"Y Zeng","year":"2022","unstructured":"Zeng, Y. et al. Spatial transcriptomics prediction from histology jointly through Transformer and graph neural networks. Brief. Bioinform. 23, bbac297 (2022).","journal-title":"Brief. Bioinform."},{"key":"4060_CR55","doi-asserted-by":"crossref","first-page":"1372","DOI":"10.1038\/s41587-023-02019-9","volume":"42","author":"D Zhang","year":"2024","unstructured":"Zhang, D. et al. Inferring super-resolution tissue architecture by integrating spatial transcriptomics with histology. Nat. Biotechnol. 42, 1372\u20131377 (2024).","journal-title":"Nat. Biotechnol."},{"key":"4060_CR56","volume":"16","author":"C Wang","year":"2025","unstructured":"Wang, C. et al. Benchmarking the translational potential of spatial gene expression prediction from histology. Nat. Commun. 16, 1544 (2025).","journal-title":"Nat. Commun."},{"key":"4060_CR57","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1038\/s41587-022-01302-5","volume":"40","author":"A Mund","year":"2022","unstructured":"Mund, A. et al. Deep Visual Proteomics defines single-cell identity and heterogeneity. Nat. Biotechnol. 40, 1231\u20131240 (2022).","journal-title":"Nat. Biotechnol."},{"key":"4060_CR58","doi-asserted-by":"crossref","first-page":"3236","DOI":"10.1038\/s41591-024-03215-z","volume":"30","author":"J Klughammer","year":"2024","unstructured":"Klughammer, J. et al. A multi-modal single-cell and spatial expression map of metastatic breast cancer biopsies across clinicopathological features. Nat. Med. 30, 3236\u20133249 (2024).","journal-title":"Nat. Med."},{"key":"4060_CR59","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1038\/s41591-023-02643-7","volume":"30","author":"M Amgad","year":"2024","unstructured":"Amgad, M. et al. A population-level digital histologic biomarker for enhanced prognosis of invasive breast cancer. Nat. Med. 30, 85\u201397 (2024).","journal-title":"Nat. Med."},{"key":"4060_CR60","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1002\/path.5310","volume":"249","author":"R Colling","year":"2019","unstructured":"Colling, R. et al. Artificial intelligence in digital pathology: a roadmap to routine use in clinical practice. J. Pathol. 249, 143\u2013150 (2019).","journal-title":"J. Pathol."},{"key":"4060_CR61","unstructured":"Yang, Y., Zha, K., Chen, Y., Wang, H. & Katabi, D. Delving into deep imbalanced regression. In Proc. International Conference on Machine Learning 11842\u201311851 (PMLR, 2021)."},{"key":"4060_CR62","doi-asserted-by":"crossref","unstructured":"Barron, J. T. A general and adaptive robust loss function. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition 4331\u20134339 (IEEE, 2019).","DOI":"10.1109\/CVPR.2019.00446"},{"key":"4060_CR63","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/s00591-010-0080-8","volume":"58","author":"F Klinker","year":"2011","unstructured":"Klinker, F. Exponential moving average versus moving exponential average. Math. Semesterber. 58, 97\u2013107 (2011).","journal-title":"Math. Semesterber."},{"key":"4060_CR64","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"W Zhou","year":"2004","unstructured":"Zhou, W., Bovik, A. C., Sheikh, H. R. & Simoncelli, E. P. Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600\u2013612 (2004).","journal-title":"IEEE Trans. Image Process."},{"key":"4060_CR65","unstructured":"Oquab, M. et al. Dinov2: learning robust visual features without supervision. Preprint at https:\/\/arxiv.org\/abs\/2304.07193 (2023)."},{"key":"4060_CR66","unstructured":"Vaswani, A. et al. Attention is all you need. In Proc. Advances in Neural Information Processing Systems Vol. 30 5998\u20136008 (Curran Associates, 2017)."},{"key":"4060_CR67","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu, M. Y. et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5, 555\u2013570 (2021).","journal-title":"Nat. Biomed. Eng."},{"key":"4060_CR68","doi-asserted-by":"crossref","first-page":"3126","DOI":"10.1109\/TPAMI.2020.2979450","volume":"43","author":"SG Zadeh","year":"2020","unstructured":"Zadeh, S. G. & Schmid, M. Bias in cross-entropy-based training of deep survival networks. IEEE Trans. Pattern Anal. Mach. Intell. 43, 3126\u20133137 (2020).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4060_CR69","unstructured":"Ilse, M., Tomczak, J. & Welling, M. Attention-based deep multiple instance learning. In Proc. International Conference on Machine Learning 2127\u20132136 (PMLR, 2018)."}],"container-title":["Nature Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41591-025-04060-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41591-025-04060-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41591-025-04060-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T15:03:09Z","timestamp":1769007789000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41591-025-04060-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":69,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4060"],"URL":"https:\/\/doi.org\/10.1038\/s41591-025-04060-4","relation":{},"ISSN":["1078-8956","1546-170X"],"issn-type":[{"value":"1078-8956","type":"print"},{"value":"1546-170X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"14 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}