{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,15]],"date-time":"2026-11-15T19:07:18Z","timestamp":1794769638076,"version":"4.9.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"vor","delay-in-days":50,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Celcomen leverages a mathematical causality framework to disentangle intra- and inter-cellular gene regulation programs in spatial transcriptomics data through a generative graph neural network. It is a first step towards perturbation models of Virtual Tissues and can generate post-perturbation counterfactual spatial transcriptomics, thereby offering access to experimentally inaccessible samples. We validated its disentanglement, identifiability of causal structure, and counterfactual prediction capabilities through simulations and in clinically relevant human glioblastoma, human fetal spleen, and mouse lung cancer samples. Celcomen provides the means to model disease- and therapy-induced changes allowing for new insights into single-cell spatially resolved tissue responses.<\/jats:p>","DOI":"10.1038\/s41467-026-69856-5","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T06:35:54Z","timestamp":1773815754000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Celcomen: spatial causal disentanglement for single-cell and tissue perturbation modeling"],"prefix":"10.1038","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2038-3040","authenticated-orcid":false,"given":"Stathis","family":"Megas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6660-6257","authenticated-orcid":false,"given":"Daniel G.","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Krzysztof","family":"Polanski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hesam","family":"Asadollahzadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moshe","family":"Eliasof","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carola-Bibiane","family":"Sch\u00f6nlieb","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6294-6366","authenticated-orcid":false,"given":"Sarah A.","family":"Teichmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"69856_CR1","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.1038\/s41588-023-01435-6","volume":"55","author":"A Sampath Kumar","year":"2023","unstructured":"Sampath Kumar, A. et al. Spatiotemporal transcriptomic maps of whole mouse embryos at the onset of organogenesis. Nat. Genet. 55, 1176\u20131185 (2023).","journal-title":"Nat. Genet."},{"key":"69856_CR2","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.1126\/science.aaw1219","volume":"363","author":"SG Rodriques","year":"2019","unstructured":"Rodriques, S. G. et al. Slide-seq: a scalable technology for measuring genome-wide expression at high spatial resolution. Science 363, 1463\u20131467 (2019).","journal-title":"Science"},{"key":"69856_CR3","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1038\/s41586-019-1049-y","volume":"568","author":"CHL Eng","year":"2019","unstructured":"Eng, C. H. L. et al. Transcriptome-scale super-resolved imaging in tissues by RNA seqFISH+. Nature 568, 235\u2013239 (2019).","journal-title":"Nature"},{"key":"69856_CR4","doi-asserted-by":"crossref","unstructured":"Janesick, A. et al. High resolution mapping of the tumor microenvironment using integrated single-cell, spatial and in situ analysis. Nat. Commun. 14, 8353 (2023).","DOI":"10.1038\/s41467-023-43458-x"},{"key":"69856_CR5","doi-asserted-by":"publisher","first-page":"4520","DOI":"10.1016\/j.cell.2024.07.035","volume":"187","author":"JE Rood","year":"2024","unstructured":"Rood, J. E., Hupalowska, A. & Regev, A. Toward a foundation model of causal cell and tissue biology with a perturbation cell and tissue Atlas. Cell 187, 4520\u20134545 (2024).","journal-title":"Cell"},{"key":"69856_CR6","doi-asserted-by":"publisher","unstructured":"Megas, S., Yayon, N., Meyer, K. B. & Id, S. A. T. Molecular connectomics: placing cells into morphological tissue context. 2\u20135 https:\/\/doi.org\/10.1371\/journal.pbio.3002803. (2024).","DOI":"10.1371\/journal.pbio.3002803"},{"key":"69856_CR7","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/s41592-019-0667-5","volume":"17","author":"R Browaeys","year":"2020","unstructured":"Browaeys, R., Saelens, W. & Saeys, Y. NicheNet: modeling intercellular communication by linking ligands to target genes. Nat. Methods 17, 159\u2013162 (2020).","journal-title":"Nat. Methods"},{"key":"69856_CR8","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1038\/s41556-022-00884-1","volume":"24","author":"E Lummertz da Rocha","year":"2022","unstructured":"Lummertz da Rocha, E. et al. CellComm infers cellular crosstalk that drives haematopoietic stem and progenitor cell development. Nat. Cell Biol. 24, 579\u2013589 (2022).","journal-title":"Nat. Cell Biol."},{"key":"69856_CR9","doi-asserted-by":"publisher","unstructured":"Tejada-Lapuerta, A., Schaar, A.C., Gutgesell, R. et al. Nicheformer: a foundation model for single-cell and spatial omics. Nat Methods 22, 2525\u20132538 https:\/\/doi.org\/10.1038\/s41592-025-02814-z (2025).","DOI":"10.1038\/s41592-025-02814-z"},{"key":"69856_CR10","doi-asserted-by":"crossref","unstructured":"Birk, S., Bonafonte-Pard\u00e0s, I., Feriz, A.M. et al. Quantitative characterization of cell niches in spatially resolved omics data. Nat Genet 57, 897\u2013909 (2025).","DOI":"10.1038\/s41588-025-02120-6"},{"key":"69856_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.crmeth.2022.100369","volume":"2","author":"MN Bernstein","year":"2022","unstructured":"Bernstein, M. N. et al. SpatialCorr identifies gene sets with spatially varying correlation structure. Cell Rep. Methods 2, 100369 (2022).","journal-title":"Cell Rep. Methods"},{"key":"69856_CR12","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1038\/s41592-022-01728-4","volume":"20","author":"Z Cang","year":"2023","unstructured":"Cang, Z. et al. Screening cell\u2013cell communication in spatial transcriptomics via collective optimal transport. Nat. Methods 20, 218\u2013228 (2023).","journal-title":"Nat. Methods"},{"key":"69856_CR13","doi-asserted-by":"crossref","unstructured":"Wilk, A. J., Shalek, A. K., Holmes, S. & Blish, C. A. Comparative analysis of cell\u2013cell communication at single-cell resolution. Nat. Biotechnol. 42, 470\u2013483 (2024).","DOI":"10.1038\/s41587-023-01782-z"},{"key":"69856_CR14","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1038\/s41587-022-01288-0","volume":"40","author":"L Jerby-Arnon","year":"2022","unstructured":"Jerby-Arnon, L. & Regev, A. DIALOGUE maps multicellular programs in tissue from single-cell or spatial transcriptomics data. Nat. Biotechnol. 40, 1467\u20131477 (2022).","journal-title":"Nat. Biotechnol."},{"key":"69856_CR15","doi-asserted-by":"publisher","unstructured":"Pearl, J. Causality (Cambridge University Press). https:\/\/doi.org\/10.1017\/CBO9780511803161. (2009).","DOI":"10.1017\/CBO9780511803161"},{"key":"69856_CR16","first-page":"2207","volume":"108","author":"I Khemakhem","year":"2020","unstructured":"Khemakhem, I., Kingma, D. P., Monti, R. P. & Hyv\u00e4rinen, A. Variational autoencoders and nonlinear ICA: a unifying framework. Proc. Mach. Learn. Res. 108, 2207\u20132217 (2020).","journal-title":"Proc. Mach. Learn. Res."},{"key":"69856_CR17","first-page":"6912","volume":"206","author":"Q Xi","year":"2023","unstructured":"Xi, Q. & Bloem-Reddy, B. Indeterminacy in generative models: characterization and strong identifiability. Proc. Mach. Learn. Res. 206, 6912\u20136939 (2023).","journal-title":"Proc. Mach. Learn. Res."},{"key":"69856_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, J. et al. Identifiability guarantees for causal disentanglement from soft interventions. Adv. Neural Inform. Process. Syst. 36, 50254\u201350292 (2023).","DOI":"10.52202\/075280-2186"},{"key":"69856_CR19","doi-asserted-by":"publisher","unstructured":"Lu, C., Wu, Y., Hern\u00e1ndez-Lobato, J. M. & Sch\u00f6lkopf, B. Nonlinear invariant risk minimization: a causal approach. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2102.12353 (2021).","DOI":"10.48550\/arXiv.2102.12353"},{"key":"69856_CR20","doi-asserted-by":"crossref","unstructured":"Suo, C. et al. Mapping the developing human immune system across organs. Science 376, eabo0510 (2022).","DOI":"10.1126\/science.abo0510"},{"key":"69856_CR21","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1016\/j.cytogfr.2008.08.004","volume":"19","author":"DJ Gough","year":"2008","unstructured":"Gough, D. J., Levy, D. E., Johnstone, R. W. & Clarke, C. J. IFN\u03b3 signaling\u2014Does it mean JAK\u2013STAT? Cytokine Growth Factor Rev. 19, 383\u2013394 (2008).","journal-title":"Cytokine Growth Factor Rev."},{"key":"69856_CR22","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1038\/s41586-023-06199-x","volume":"618","author":"B Kruse","year":"2023","unstructured":"Kruse, B. et al. CD4+ T cell-induced inflammatory cell death controls immune-evasive tumours. Nature 618, 1033\u20131040 (2023).","journal-title":"Nature"},{"key":"69856_CR23","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.ejcsup.2013.07.013","volume":"11","author":"JBAG Haanen","year":"2013","unstructured":"Haanen, J. B. A. G. Immunotherapy of melanoma. Eur. J. Cancer, Suppl. 11, 97\u2013105 (2013).","journal-title":"Eur. J. Cancer, Suppl."},{"key":"69856_CR24","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41577-021-00566-3","volume":"22","author":"AM Gocher","year":"2022","unstructured":"Gocher, A. M., Workman, C. J. & Vignali, D. A. A. Interferon-\u03b3: teammate or opponent in the tumour microenvironment? Nat. Rev. Immunol. 22, 158\u2013172 (2022).","journal-title":"Nat. Rev. Immunol."},{"key":"69856_CR25","doi-asserted-by":"publisher","first-page":"13925","DOI":"10.1074\/jbc.R116.774745","volume":"292","author":"DS Green","year":"2017","unstructured":"Green, D. S., Young, H. A. & Valencia, J. C. Current prospects of type II interferon \u03b3 signaling & autoimmunity. J. Biol. Chem. 292, 13925\u201313933 (2017).","journal-title":"J. Biol. Chem."},{"key":"69856_CR26","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1038\/s41564-019-0421-x","volume":"4","author":"EV Mesev","year":"2019","unstructured":"Mesev, E. V., LeDesma, R. A. & Ploss, A. Decoding type I and III interferon signalling during viral infection. Nat. Microbiol. 4, 914\u2013924 (2019).","journal-title":"Nat. Microbiol."},{"key":"69856_CR27","doi-asserted-by":"publisher","first-page":"101277","DOI":"10.1016\/j.smim.2019.05.001","volume":"43","author":"S Lukhele","year":"2019","unstructured":"Lukhele, S., Boukhaled, G. M. & Brooks, D. G. Type I interferon signaling, regulation and gene stimulation in chronic virus infection. Semin. Immunol. 43, 101277 (2019).","journal-title":"Semin. Immunol."},{"key":"69856_CR28","doi-asserted-by":"publisher","first-page":"116","DOI":"10.3389\/fonc.2012.00116","volume":"2","author":"K Lauber","year":"2012","unstructured":"Lauber, K., Ernst, A., Orth, M., Herrmann, M. & Belka, C. Dying cell clearance and its impact on the outcome of tumor radiotherapy. Front. Oncol. 2, 116 (2012).","journal-title":"Front. Oncol."},{"key":"69856_CR29","doi-asserted-by":"crossref","unstructured":"Farah, E. N. et al. Spatially organized cellular communities form the developing human heart. Nature 627, 854\u2013864 (2024).","DOI":"10.1038\/s41586-024-07171-z"},{"key":"69856_CR30","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1038\/s41586-023-06311-1","volume":"619","author":"K Kanemaru","year":"2023","unstructured":"Kanemaru, K. et al. Spatially resolved multiomics of human cardiac niches. Nature 619, 801\u2013810 (2023).","journal-title":"Nature"},{"key":"69856_CR31","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41586-023-06812-z","volume":"624","author":"Z Yao","year":"2023","unstructured":"Yao, Z. et al. A high-resolution transcriptomic and spatial atlas of cell types in the whole mouse brain. Nature 624, 317\u2013332 (2023).","journal-title":"Nature"},{"key":"69856_CR32","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1038\/s41586-024-07575-x","volume":"631","author":"RGH Lindeboom","year":"2024","unstructured":"Lindeboom, R. G. H. et al. Human SARS-CoV-2 challenge uncovers local and systemic response dynamics. Nature 631, 189\u2013198 (2024).","journal-title":"Nature"},{"key":"69856_CR33","doi-asserted-by":"publisher","unstructured":"Zhang, B. et al. A human embryonic limb cell atlas resolved in space and time. Nature https:\/\/doi.org\/10.1038\/s41586-023-06806-x. (2023).","DOI":"10.1038\/s41586-023-06806-x"},{"key":"69856_CR34","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1086\/525638","volume":"74","author":"F Eberhardt","year":"2007","unstructured":"Eberhardt, F. & Scheines, R. Interventions and causal inference. Philos. Sci. 74, 981\u2013995 (2007).","journal-title":"Philos. Sci."},{"key":"69856_CR35","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1007\/s10208-022-09581-9","volume":"23","author":"C Squires","year":"2022","unstructured":"Squires, C. & Uhler, C. Causal structure learning: a combinatorial perspective. Found. Comput. Math. 23, 1781\u20131815 (2022).","journal-title":"Found. Comput. Math."},{"key":"69856_CR36","unstructured":"Meek, Christopher. Related Graphical Frameworks: Undirected, Directed Acyclic and Chain Graph Models. Technical Report No. 64. Pittsburgh, PA: Department of Philosophy, Carnegie Mellon University, 1995."},{"key":"69856_CR37","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1126\/science.298.5594.824","volume":"298","author":"R Milo","year":"2002","unstructured":"Milo, R. et al. Network Motifs: simple building blocks of complex networks. Science 298, 824\u2013827 (2002).","journal-title":"Science"},{"key":"69856_CR38","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-017-1382-0","volume":"19","author":"FA Wolf","year":"2018","unstructured":"Wolf, F. A., Angerer, P. & Theis, F. J. SCANPY: large-scale single-cell gene expression data analysis. Genome Biol. 19, 15 (2018).","journal-title":"Genome Biol."},{"key":"69856_CR39","doi-asserted-by":"publisher","first-page":"3045","DOI":"10.1002\/pmic.200800002","volume":"8","author":"EC Dimmer","year":"2008","unstructured":"Dimmer, E. C. et al. The gene ontology \u2014 providing a functional role in proteomic studies. Proteomics 8, 3045\u20133046 (2008).","journal-title":"Proteomics"},{"key":"69856_CR40","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1016\/j.cell.2022.02.015","volume":"185","author":"M Dhainaut","year":"2022","unstructured":"Dhainaut, M. et al. Spatial CRISPR genomics identifies regulators of the tumor microenvironment. Cell 185, 1223\u20131239.e20 (2022).","journal-title":"Cell"},{"key":"69856_CR41","unstructured":"Megas, S., Asadollahzadeh, H. & Polanski, K. github.com\/Teichlab\/celcomen: v1.0.0. (2025)."},{"key":"69856_CR42","unstructured":"Chen, D. G. & Megas, S. github.com\/stathismegas\/celcomen_reproducibility: v1.0.0. (2025)."}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-69856-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-69856-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-69856-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T15:07:54Z","timestamp":1778425674000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-69856-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["69856"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-69856-5","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]},"assertion":[{"value":"7 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"In the past three years, S.A.T. has received remuneration for scientific advisory board membership from Sanofi, GlaxoSmithKline, Foresite Labs and Qiagen. S.A.T. is a co-founder and holds equity in Transition Bio and Ensocell. From January 8th of 2024, S.A.T. is a part-time employee of GlaxoSmithKline. The remaining authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"4126"}}