Abstract
Spatial transcriptomics (ST) has emerged as a powerful tool for analyzing cell-cell communication (CCC) across various biological processes, ranging from embryonic development to cancer progression. However, its limited resolution and high data sparsity hinder the detailed characterization of CCC patterns within complex tissues. Here, we introduce FineST, a deep contrastive learning model that leverages a histology foundation model to fuse ST and histology images, enabling Fine-grained Spatial Transcriptomics analysis. This approach facilitates precise nuclei segmentation, high-resolution RNA expression imputation, and the identification of intricate ligand-receptor interactions. Using both colorectal cancer VisiumHD and breast cancer Xenium datasets, we demonstrate that FineST significantly outperforms existing methods in high-resolution RNA imputation, cell type prediction, and CCC pattern discovery. With focused application to the Visium platform, FineST reveals novel biological insights into tumor-immune interactions across multiple cancer types, including invasive fronts in breast cancer, tertiary lymphoid structures in nasopharyngeal carcinoma, and PD-1 therapy resistance barriers in hepatocellular carcinoma. These findings highlight a new paradigm in ST analysis through the integration of readily available histology images.
Similar content being viewed by others
Data availability
The VisiumHD data and Chromium Single Cell Gene Expression Flex of human colorectal cancer (CRC) were downloaded from the 10x Genomics datasets here: https://www.10xgenomics.com/products/visium-hd-spatial-gene-expression/dataset-human-crc with ‘Visium HD, Sample P2 CRC’ and ‘Chromium Single Cell Flex, aggregated’ Files. The raw and processed Visium, Xenium spatial sequencing data, and Chromium Single Cell Gene Expression Flex of human breast cancer (BRCA) tissues were downloaded from 10x Genomics https://www.10xgenomics.com/products/xenium-in-situ/preview-dataset-human-breast with ‘Visium Spatial’, ‘In Situ Sample 1, Replicate 1’ and ‘FRP’ Files, and GEO under accession number GSE243280 with ‘GSM7782699’, ‘GSM7780153’ and ‘GSM7782698’ Samples. Cell type annotations for Xenium, Visium, and Chromium Flex datasets of BRCA are available for download in the ‘Cell Type Annotations’ Section. The raw and processed Visium spatial sequencing data of human hepatocellular carcinoma (HCC) tissues were downloaded from Mendeley Data under accession number skrx2fz79n [https://data.mendeley.com/datasets/skrx2fz79n/1], while the cell type annotations and high-resolution HE-stained images were provided by the original corresponding author. The raw and processed Visium spatial sequencing data of human primary nasopharyngeal carcinoma (NPC) tissues were downloaded from GEO under accession number GSE200310. The integrated scRNA-seq data of NPC were obtained from our colleagues and are available from the corresponding author upon request. For easier reuse, we also included them in the FineST Python package as follows: the CRC data: FineST.datasets.CRC16um(), FineST.datasets.CRC08um(), the BRCA data FineST.datasets.BRCA(), the HCC data FineST.datasets.HCCP1T(), FineST.datasets.HCCP7T(), and the NPC data FineST.datasets.NPC(). The ligand-receptor databases are available from the CellChat repository: https://github.com/sqjin/CellChat/tree/master/data. Source data are provided with this paper.
Code availability
The FineST algorithm is a publicly available Python package at https://github.com/StatBiomed/FineST and https://doi.org/10.5281/zenodo.834361664. Detailed documentation and analysis notebooks to reproduce results in this paper are also included in this repository (https://finest-rtd-tutorial.readthedocs.io). All data analyzed in this work are available through the figshare link: https://figshare.com/articles/dataset/FineST_supplementary_data/26763241.
References
Armingol, E., Baghdassarian, H. M. & Lewis, N. E. The diversification of methods for studying cell–cell interactions and communication. Nat. Rev. Genet. 25, 381–400 (2024).
Vento-Tormo, R. et al. Single-cell reconstruction of the early maternal–fetal interface in humans. Nature 563, 347–353 (2018).
He, S. et al. Starfysh integrates spatial transcriptomic and histologic data to reveal heterogeneous tumor-immune hubs. Nat. Biotechnol. 43, 223–235 (2025).
Efremova, M., Vento-Tormo, M., Teichmann, S. A. & Vento-Tormo, R. CellPhoneDB: Inferring cell–cell communication from combined expression of multi-subunit ligand–receptor complexes. Nat. Protoc. 15, 1484–1506 (2020).
Jin, S. et al. Inference and analysis of cell-cell communication using CellChat. Nat. Commun. 12, 1088 (2021).
Wilk, A. J, Shalek, A. K, Holmes, S. & Blish, C. A. Comparative analysis of cell-cell communication at single-cell resolution. Nat. Biotechnol. 42, 470–483 (2024).
Li, Z., Wang, T., Liu, P. & Huang, Y. SpatialDM for rapid identification of spatially co-expressed ligand-receptor and revealing cell-cell communication patterns. Nat. Commun. 14, 3995 (2023).
Cang, Z. et al. Screening cell-cell communication in spatial transcriptomics via collective optimal transport. Nat. Methods 20, 218–228 (2023).
Zhu, J. et al. Mapping cellular interactions from spatially resolved transcriptomics data. Nat. Methods 21, 1830–1842 (2024).
Chen, H., Li, D. & Bar-Joseph, Z. SCS: Cell segmentation for high-resolution spatial transcriptomics. Nat. Methods 20, 1237–1243 (2023).
Dimitrov, D. et al. LIANA+ provides an all-in-one framework for cell–cell communication inference. Nat. Cell Biol. 26, 1613–1622 (2024).
Ren, J., Luo, S., Shi, H. & Wang, X. Spatial omics advances for in situ RNA biology. Mol. Cell 84, 3737–3757 (2024).
Tian, L., Chen, F. & Macosko, E. Z. The expanding vistas of spatial transcriptomics. Nat. Biotechnol. 41, 773–782 (2023).
Hu, J. et al. Deciphering tumor ecosystems at super resolution from spatial transcriptomics with TESLA. Cell Syst. 14, 404–417 (2023).
Oliveira, M. F. et al. High-definition spatial transcriptomic profiling of immune cell populations in colorectal cancer. Nat. Genet. 57, 1512–1523 (2025).
Graham, S. et al. Hover-Net: simultaneous segmentation and classification of nuclei in multi-tissue histology images. Med. Image Anal. 58, 101563 (2019).
Fu, Y. et al. Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. Nat. Cancer 1, 800–810 (2020).
Xu, H. et al. A whole-slide foundation model for digital pathology from real-world data. Nature 630, 181–188 (2024).
Zhao, W., Liang, Z., Huang, X., Huang, Y. & Yu, L. Hist2Cell: deciphering fine-grained cellular architectures from histology images. Cell Genomics, 6, 101137 (2026).
He, B. et al. Integrating spatial gene expression and breast tumour morphology via deep learning. Nat. Biomed. Eng. 4, 827–834 (2020).
Xie, R. et al. Spatially resolved gene expression prediction from histology images via bi-modal contrastive learning. Advances in Neural Information Processing Systems 36 (2024).
Ash, J. T., Darnell, G., Munro, D. & Engelhardt, B. E. Joint analysis of expression levels and histological images identifies genes associated with tissue morphology. Nat. Commun. 12, 1609 (2021).
Fu, X. et al. Spatial gene expression at single-cell resolution from histology using deep learning with GHIST. Nat. Methods 22, 1900–1910 (2025).
Bergenstråhle, L. Super-resolved spatial transcriptomics by deep data fusion. Nat. Biotechnol. 40, 476–479 (2022).
Zhang, D. et al. Inferring super-resolution tissue architecture by integrating spatial transcriptomics with histology. Nat. Biotechnol. 42, 1372–1377 (2024).
Zimmermann, E. et al. Virchow2: scaling self-supervised mixed magnification models in pathology. Preprint at arXiv https://doi.org/10.48550/arXiv.2408.00738 (2024).
Wang, T.Li, L. & Huang, Y. SparseAEH: scalable autoregressive expression histology discovery in spatial transcriptomics via sparse Gaussian kernels. Preprint at bioRxiv https://doi.org/10.64898/2026.01.22.701193 (2026).
Svensson, V., Teichmann, S. A. & Stegle, O. SpatialDE: identification of spatially variable genes. Nat. Methods 15, 343–346 (2018).
Vishnubalaji, R. et al. Bone morphogenetic protein 2 (BMP2) induces growth suppression and enhances chemosensitivity of human colon cancer cells. Cancer Cell Int. 16, 1–12 (2016).
Kamel, M. et al. ENACT: End-to-end analysis of Visium High Definition (HD) data. Bioinformatics 41, btaf094 (2025).
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).
Qiao, C. & Huang, Y. Reliable imputation of spatial transcriptome with uncertainty estimation and spatial regularization. Patterns 5, 101021 (2024).
Liu, M. et al. INHBA is a mediator of aggressive tumor behavior in HER2+ basal breast cancer. Breast Cancer Res. 24, 18 (2022).
McCluney, S. et al. Anti-activin treatment increases T cell infiltration in breast and pancreatic tumours and promotes survival in a SMAD4-null mouse pancreatic cancer model. Preprint at bioRxiv https://doi.org/10.1101/2025.06.13.659133 (2025).
Berdiel-Acer, M. et al. Stromal NRG1 in luminal breast cancer defines pro-fibrotic and migratory cancer-associated fibroblasts. Oncogene 40, 2651–2666 (2021).
Chen, Y., Lu, A., Hu, Z., Li, J. & Lu, J. ERBB3 targeting: a promising approach to overcoming cancer therapeutic resistance. Cancer Lett. 599, 217146 (2024).
Deshpande, A. et al. Uncovering the spatial landscape of molecular interactions within the tumor microenvironment through latent spaces. Cell Syst. 14, 285–301 (2023).
Gong, L. et al. Nasopharyngeal carcinoma cells promote regulatory T cell development and suppressive activity via CD70-CD27 interaction. Nat. Commun. 14, 1912 (2023).
Gong, L. et al. Comprehensive single-cell sequencing reveals the stromal dynamics and tumor-specific characteristics in the microenvironment of nasopharyngeal carcinoma. Nat. Commun. 12, 1540 (2021).
Chen, C., Zhang, Y., Wu, X. & Shen, J. The role of tertiary lymphoid structure and B cells in nasopharyngeal carcinoma: based on bioinformatics and experimental verification. Transl. Oncol. 41, 101885 (2024).
Lavie, D., Ben-Shmuel, A., Erez, N. & Scherz-Shouval, R. Cancer-associated fibroblasts in the single-cell era. Nat. Cancer 3, 793–807 (2022).
Li, X., Guo, Y., Xiao, M. & Zhang, W. The immune escape mechanism of nasopharyngeal carcinoma. FASEB J. 37, e23055 (2023).
Jin, S. et al. Single-cell transcriptomic analysis defines the interplay between tumor cells, viral infection, and the microenvironment in nasopharyngeal carcinoma. Cell Res. 30, 950–965 (2020).
Liao, Y. et al. Microbes translocation from the oral cavity to the nasopharyngeal carcinoma in patients. Nat. Commun. 15, 1645 (2024).
Chen, B. et al. N7-methylguanosine tRNA modification promotes tumorigenesis and chemoresistance through WNT/β-catenin pathway in nasopharyngeal carcinoma. Oncogene 41, 2239–2253 (2022).
Sautès-Fridman, C., Petitprez, F., Calderaro, J. & Fridman, W. H. Tertiary lymphoid structures in the era of cancer immunotherapy. Nat. Rev. Cancer 19, 307–325 (2019).
You, R. et al. Single-cell and spatial transcriptomics reveal mechanisms of radioresistance and immune escape in recurrent nasopharyngeal carcinoma. Nat. Genet. 57, 1950–1965 (2025).
Liu, Y. et al. Identification of a tumour immune barrier in the HCC microenvironment that determines the efficacy of immunotherapy. J. Hepatol. 78, 770–782 (2023).
Le, K. et al. Blockade of CCR1 induces a phenotypic shift in macrophages and triggers a favorable antilymphoma activity. Blood Adv. 7, 3952–3967 (2023).
Iwai, Y. et al. Involvement of PD-L1 on tumor cells in the escape from the host immune system and tumor immunotherapy by PD-L1 blockade. Proc. Natl. Acad. Sci. 99, 12293–12297 (2002).
Wolf, F. A., Angerer, P. & Theis, F. J. SCANPY: Large-scale single-cell gene expression data analysis. Genome Biol. 19, 1–5 (2018).
Wan, X. et al. Integrating spatial and single-cell transcriptomics data using deep generative models with SpatialScope. Nat. Commun. 14, 7848 (2023).
Schmidt, U.Weigert, M.Broaddus, C. & Myers, G. Cell detection with star-convex polygons. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part II 11, 265–273 (Springer, 2018).
Chen, R. J. et al. Scaling vision transformers to gigapixel images via hierarchical self-supervised learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16144–16155 (2022).
Li, S. et al. CellContrast: reconstructing spatial relationships in single-cell RNA sequencing data via deep contrastive learning. Patterns 5, 101022 (2024).
Chiu, C.-L.,C. lack,N. et al. Napari: a Python multi-dimensional image viewer platform for the research community. Microsc. Microanal. 28, 1576–1577 (2022).
Marconato, L. et al. SpatialData: an open and universal data framework for spatial omics. Nat. Methods 22, 58–62 (2025).
Ding, Q. et al. Dimension reduction, cell clustering, and cell–cell communication inference for single-cell transcriptomics with DcjComm. Genome Biol. 25, 241 (2024).
Baruzzo, G., Cesaro, G. & Di Camillo, B. Identify, quantify and characterize cellular communication from single-cell RNA sequencing data with scSeqComm. Bioinformatics 38, 1920–1929 (2022).
Li, B., Wang, C., Wang, Y., Li, P. & Liu, Z.-P. RegNetwork 2025: An integrative data repository for gene regulatory networks in human and mouse. Nucleic Acids Research, gkaf779 (2025).
Otasek, D., Morris, J. H., Boucas, J., Pico, A. R. & Demchak, B. Cytoscape automation: Empowering workflow-based network analysis. Genome Biol. 20, 185 (2019).
Ban, M. et al. Expression profiling of cerebrospinal fluid identifies dysregulated antiviral mechanisms in multiple sclerosis. Brain 147, 554–565 (2024).
Kaminow, B., Yunusov, D. & Dobin, A. STARsolo: accurate, fast and versatile mapping/quantification of single-cell and single-nucleus RNA-seq data. Preprint at biorxiv https://doi.org/10.1101/2021.05.05.442755 (2021).
Li, L. & Huang, Y. FineST: Contrastive learning integrates histology and spatial transcriptomics for nuclei-resolved ligand-receptor analysis. Zenodo https://doi.org/10.5281/zenodo.18642322 (2026).
Acknowledgments
We kindly thank Dr. Lanqi Gong and Dr. Wei Dai from the Department of Clinical Oncology, the University of Hong Kong, for sharing the NPC dataset and providing biological insights. We also thank Dr. Youqiong Ye and Dr. Zhenzhen Xun from the School of Medicine, Shanghai Jiao Tong University, for sharing high-resolution HE-stained images and cell type annotations of the HCC dataset. We are grateful to StatBiomed lab members, especially Dr. Shumin Li for the contrastive model and Dr. Ruiyan Hou for package efficiency. This project is supported by the Research Grants Council of the Hong Kong SAR, China (grant numbers T12-705-24-R, YCRG-C7004-22Y, and 17126725), the National Natural Science Foundation of China (grant number 62222217), the InnoHK initiative of the Innovation and Technology Commission of the Hong Kong Special Administrative Region Government, and the University of Hong Kong through a startup fund and a seed fund (Y.H.), a PDF scheme (L.L.) and a Postgraduate Scholarship (T.W.). This project is also supported in part by the Research Grants Council of Hong Kong (17200125 and T45-401/22-N) (L.Y.), the Research Grants Council of Hong Kong (Research Fellow Scheme RFS2122-7S05) and Croucher Foundation Senior Research Fellowship (S.M). S.M. is also a Jimmy and Emily Tang Professor in Molecular Genetics.
Author information
Authors and Affiliations
Contributions
Y.H. conceived and supervised this study with support from L.Y. L.L. implemented the FineST and performed all data analysis. T.W. implemented SparseAEH for rapid CCC pattern identification. Z.L. and L.Y. assisted with the image modeling. H.Y. and S.M. provided valuable biological insights on HCC. L.L. and Y.H. wrote the manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Peer review
Peer review information
Nature Communications thanks Qing Nie and the other anonymous reviewer(s) for their contribution to the peer review of this work. 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.
Source data
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, 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 changes were made. 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/4.0/.
About this article
Cite this article
Li, L., Wang, T., Liang, Z. et al. FineST: contrastive learning integrates histology and spatial transcriptomics for nuclei-resolved ligand-receptor analysis. Nat Commun (2026). https://doi.org/10.1038/s41467-026-70528-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41467-026-70528-7
