Abstract
Spatial transcriptomics is an emerging technology that can analyze gene expression profiles of tissues while preserving spatial location information. To restore cell type proportions from mixed gene expression data, here we present DANST, a deconvolution framework based on deep domain adversarial neural networks. By integrating single-cell RNA sequencing (scRNA-seq) with inferred spatial coordinates, we construct pseudo-spatial data. DANST utilizes a variational autoencoder to learn refined feature representations and introduces a domain adversarial architecture to align feature distributions between pseudo and real data, enabling accurate label transfer. Benchmarking on human and mouse datasets shows that DANST achieves superior deconvolution accuracy compared with existing methods. These findings highlight its effectiveness for tumor microenvironment analysis and potential clinical utility.
Similar content being viewed by others
Data availability
We use six sets of ST data and the corresponding scRNA-seq data. Three of them are artificially synthesized data, which are the datasets used by Wang et al.16 to conduct benchmark experiments and can be downloaded at https://figshare.com/articles/dataset/SpatialcoGCN_data/22682611. The other three sets are real data, namely the mouse brain anterior dataset, the mouse brain coronal slice dataset, and the human breast cancer dataset. The ST data of the mouse brain anterior dataset is obtained from the 10x Genomics dataset2 (https://www.10xgenomics.com/resources/datasets), and the corresponding scRNA-seq data is acquired from the whole cortex and hippocampus of the mouse (https://portal.brain-map.org/atlases-and-data/rnaseq/mouse-whole-cortex-and-hippocampus-10x). The ST data and corresponding scRNA-seq data of the mouse brain coronal section dataset are collected from the 10x Genomics dataset and E-MTAB-1111542 (https://www.ebi.ac.uk/biostudies/arrayexpress/studies/EMTAB-11115), respectively. The ST data of the human breast cancer dataset is retrieved from https://www.10xgenomics.com/resources/datasets/human-breast-cancer-block-asection-1-1-standard-1-1-0, and the scRNA-seq data is downloaded from the database DISCO43 (https://www.immunesinglecell.org/). The data used in this study have been uploaded to Zenodo and is freely available at: https://doi.org/10.5281/zenodo.1821306144. All source data underlying the graphs and charts are provided as Supplementary Data 1, Supplementary Data 2, Supplementary Data 3, and Supplementary Data 4. All other data supporting the findings of this study are available from the corresponding author upon reasonable request.
Code availability
An open-source Python implementation of the DANST toolkit is accessible at https://github.com/ZhichaoWu7/DANST.The version of the code described in this paper has been deposited in Zenodo with the identifier https://doi.org/10.5281/zenodo.1821215045.
References
Smith, K. D., Prince, D. K., MacDonald, J. W., Bammler, T. K. & Akilesh, S. Challenges and opportunities for the clinical translation of spatial transcriptomics technologies. Glomerular Dis. 4, 49–63 (2024).
Asp, M., Bergenstråhle, J. & Lundeberg, J. Spatially resolved transcriptomes—next generation tools for tissue exploration. Bioessays 42, e1900221 (2020).
10x Genomics. https://www.10xgenomics.com/resources/datasets/ (2023).
Rodriques, S. G. et al. Slide-seq: a scalable technology for measuring genome-wide expression at high spatial resolution. Science 363, 1463–1467 (2019).
Liu, Y. et al. High-spatial-resolution multi-omics sequencing via deterministic barcoding in tissue. Cell 183, 1665–1681 (2020).
Chen, A. et al. Spatiotemporal transcriptomic atlas of mouse organogenesis using DNA nanoball-patterned arrays. Cell 185, 1777–1792 (2022).
Fu, X. et al. Polony gels enable amplifiable DNA stamping and spatial transcriptomics of chronic pain. Cell 185, 4621–4633 (2022).
Cho, C.-S. et al. Microscopic examination of spatial transcriptome using seq-scope. Cell 184, 3559–3572.e22 (2021).
Eng, C.-H. L. et al. Transcriptome-scale super-resolved imaging in tissues by RNA seqFISH. Nature 568, 235–239 (2019).
Cable, D. M. et al. Robust decomposition of cell type mixtures in spatial transcriptomics. Nat. Biotechnol. 40, 517–526 (2022).
Elosua-Bayes, M., Nieto, P., Mereu, E., Gut, I. & Heyn, H. SPOTlight: seeded NMF regression to deconvolute spatial transcriptomics spots with single-cell transcriptomes. Nucleic Acids Res. 49, e50 (2021).
Andersson, A. et al. Spatial mapping of cell types by integration of transcriptomics data. Commun. Biol. 3, 77 (2020).
Kleshchevnikov, V. et al. Cell2location maps fine-grained cell types in spatial transcriptomics. Nat. Biotechnol. 40, 661–671 (2022).
Garmire, L. X. et al. Challenges and perspectives in computational deconvolution of genomics data. Nat. Methods 21, 391–400 (2024).
Xu, H. et al. SPACEL: deep learning-based characterization of spatial transcriptome architectures. Nat. Commun. 14, 7603 (2023).
Li, H., Li, H., Zhou, J. & Gao, X. SD2: spatially resolved transcriptomics deconvolution through integration of dropout and spatial information. Bioinformatics. 38, 4878–4884 (2022).
Long, Y. et al. Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with GraphST. Nat. Commun. 14, 1155 (2023).
Wang, Y., Wan, Y. & Zhou, Y. SpatialcoGCN: deconvolution and spatial information–aware simulation of spatial transcriptomics data via deep graph co-embedding. Brief. Bioinform. 25, bbae130 (2024).
Coleman, K. et al. SpaDecon: cell-type deconvolution in spatial transcriptomics with semi-supervised learning. Commun. Biol. 6, 378 (2023).
Biancalani, T. et al. Deep learning and alignment of spatially resolved single-cell transcriptomes with Tangram. Nat Methods 18, 1352–1362 (2021).
Bae, S. et al. CellDART: cell type inference by domain adaptation of single-cell and spatial transcriptomic data. Nucleic Acids Res. 50, e57 (2022).
Bae, S., Choi, H. & Lee, D. S. spSeudoMap: cell type mapping of spatial transcriptomics using unmatched single-cell RNA-seq data. Genome Med. 15, 19 (2023).
Liu, Z. et al. SONAR enables cell type deconvolution with spatially weighted Poisson-Gamma model for spatial transcriptomics. Nat. Commun. 14, 4727 (2023).
Davis, J. & Goadrich, M. An introduction to ROC analysis. Pattern Recognit. Lett. 27, 861–874 (2006).
Ståhl, P. L. et al. Visualization and analysis of gene expression in tissue sections by spatial transcriptomics. Science 353, 78–82 (2016).
Tasic, B. et al. Shared and distinct transcriptomic cell types across neocortical areas. Nature. 563, 72–78 (2018).
Wu, S. Z. et al. A single-cell and spatially resolved atlas of human breast cancers. Nat. Genet. 53, 1334–1347 (2021).
Yang, W. et al. Single-cell RNA reveals a tumorigenic microenvironment in the interface zone of human breast tumors. Breast Cancer Res. 25, 100 (2023).
Kumar, T. et al. A spatially resolved single-cell genomic atlas of the adult human breast. Nature 620, 181–191 (2023).
Keren, L. et al. A structured tumor-immune microenvironment in triple negative breast cancer revealed by multiplexed ion beam imaging. Cell 174, 1373–1387 (2018).
Carron, E. C. et al. Macrophages promote the progression of premalignant mammary lesions to invasive cancer. Oncotarget 8, 50731–50746 (2017).
Hu, Q. et al. Atlas of breast cancer infiltrated B-lymphocytes revealed by paired single-cell RNA-sequencing and antigen receptor profiling. Nat. Commun. 12, 2186 (2021).
Roy, M., Fowler, A. M., Ulaner, G. A. & Mahajan, A. Molecular Classification of Breast Cancer. PET Clin. 18, 441–458 (2023).
Song, Y. et al. DDHD2 is involved in the malignant progression of early luminal A breast cancer by changing cell membrane proteins and immune responses functionality. Oncol. Transl. Med. 10, 231–244 (2024).
Subramanian, A. et al. Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles. Proc. Natl. Acad. Sci. USA 102, 15545–15550 (2005).
Wolf, F. A., Angerer, P. & Theis, F. J. SCANPY: large-scale single-cell gene expression data analysis. Genome Biol. 19, 15 (2018).
McCarthy, D. J., Campbell, K. R., Lun, A. T. L. & Wills, Q. F. Scater: pre-processing, quality control, normalization and visualization of single-cell RNA-seq data in R. Bioinformatics 33, 1179–1186 (2017).
Fraley, C., Raftery, A. E., Murphy, T. B. & Scrucca, L. mclust Version 4 for R: Normal Mixture Modeling for Model-Based Clustering, Classification, and Density Estimation. Report No. 597 (University of Washington, 2012).
Ganin, Y. et al. Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 1–35 (2016).
Fey, M. & Lenssen, J. E. Fast graph representation learning with PyTorch geometric. ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds. (ICLR, 2019).
Bock, S., & Weiß, M. A proof of local convergence for the Adam optimizer. IEEE International Joint Conference on Neural Networks (IEEE, 2019).
Kleshchevnikov V., et al. Single-nucleus RNA-seq from adult mouse brain sections paired to 10X Visium spatial RNA-seq. E-MTAB-11115, (EMBL-EBI, 2022).
Li, M. et al. DISCO: a database of deeply integrated human singlecell omics data. Nucleic Acids Res. 50, D596–D602 (2022).
Wu, Z. Processed datasets for DANST enables cell-type deconvolution in spatial transcriptomics using deep domain adversarial neural networks. Zenodo https://doi.org/10.5281/zenodo.18213061 (2026).
Wu, Z. ZhichaoWu7/DANST: First version for publication (v1.0.0). Zenodo https://doi.org/10.5281/zenodo.18212150 (2026).
Acknowledgements
This work was partially supported by the National Natural Science Foundation of China (NSFC No.51975213) and Clinical Project of Shanghai Municipal Health Commission (No.202340054).
Author information
Authors and Affiliations
Contributions
X.Z. and T.W. envisaged the project and wrote the manuscript. T.W. and Z.W. implemented the model and code, performed the experiments. H.Z., Y.Z., and W.D. analyzed and interpreted data of S.T., and validated the final method. X.Z. and Q.Z. provided model evaluation and critical manuscript revision. All authors read and approved the final manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Peer review
Peer review information
Communications Biology thanks Yanghong Guo, Nam D. Nguyen and Chitrasen Mohanty for their contribution to the peer review of this work. Primary Handling Editors: Laura Rodríguez Pérez. A peer review file is available.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Zhang, X., Wu, Z., Wang, T. et al. DANST enables cell-type deconvolution in spatial transcriptomics using deep domain adversarial neural networks. Commun Biol (2026). https://doi.org/10.1038/s42003-026-09659-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s42003-026-09659-y
