Abstract
The spatial position of cells within tissues and organs is crucial for the manifestation of their specific functions. Spatial transcriptomics technology enables comprehensive measurement of the gene expression patterns in tissues while retaining spatial information. However, current popular spatial transcriptomics techniques either have shallow sequencing depth or low resolution. We present stEnTrans, a deep learning method based on Transformer architecture that provides comprehensive predictions for gene expression in unmeasured or unexpectedly lost areas and enhances gene expression in original and imputed spots. Utilizing self-supervised learning approach, stEnTrans establishes proxy tasks on gene expression profiles without requiring additional data, mining intrinsic features of the tissues as supervisory information. We evaluate stEnTrans on six datasets and the results indicate superior performance in enhancing spatial resolution and predicting gene expression in unmeasured areas compared to other deep learning and traditional interpolation methods. Additionally, stEnTrans can also help the discovery of spatial patterns in spatial transcriptomics and enrich to more biologically significant pathways. Our source code is available at https://github.com/shuailinxue/stEnTrans.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Moses, L., Pachter, L.: Museum of spatial transcriptomics. Nat. Methods 19(5), 534–546 (2022)
Li, Q., Zhang, X., et al.: Spatial transcriptomics for tumor heterogeneity analysis. Front. Genet. 13(2), 906158 (2022)
Lohoff, T., Ghazanfar, S., et al.: Integration of spatial and single-cell transcriptomic data elucidates mouse organogenesis. Nat. Biotechnol. 40(1), 74–85 (2022)
Hasel, P., Rose, I.V.L., et al.: Neuroinflammatory astrocyte subtypes in the mouse brain. Nat. Neurosci. 24(10), 1475–1487 (2021)
Asp, M., Bergenstråhle, J., et al.: Spatially resolved transcriptomes-next generation tools for tissue exploration. BioEssays 42(10), 1900221 (2020)
Rao, N., Clark, S., et al.: Bridging genomics and tissue pathology: 10x genomics explores new frontiers with the visium spatial gene expression solution. Genetic Eng. Biotechnol. News 40(2), 50–51 (2020)
Thrane, K., Eriksson, H., et al.: Spatially resolved transcriptomics enables dissection of genetic heterogeneity in stage III cutaneous malignant melanoma. Can. Res. 78(20), 5970–5979 (2018)
**g, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 4037–4058 (2020)
He, Y., Tang, X., et al.: ClusterMap for multi-scale clustering analysis of spatial gene expression. Nat. Commun. 12(1), 5909 (2021)
Janesick, A., Shelansky, R., et al.: High resolution map** of the breast cancer tumor microenvironment using integrated single cell, spatial and in situ analysis of FFPE tissue. Nat. Commun. 14(1), 5353 (2023)
Li, X., Min, W., et al.: TransVCOX: bridging transformer encoder and pre-trained VAE for robust cancer multi-omics survival analysis. In: 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1254–1259 (2023)
Vaswani, A., Shazeer, N., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 14, 1–11 (2017)
Dosovitskiy, A., Beyer, L., et al.: An image is worth 16 \(\times \) 16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations, pp. 1–22 (2021)
He, K., Zhang, X., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Zhao, Y., Wang, K., et al.: DIST: spatial transcriptomics enhancement using deep learning. Briefings Bioinform. 24(2), bbad013 (2023)
Li, X., Orchard, M.T.: New edge-directed interpolation. IEEE Trans. Image Process. 10(10), 1521–1527 (2001)
Zhao, E., Stone, M.R., et al.: Spatial transcriptomics at subspot resolution with BayesSpace. Nat. Biotechnol. 39(11), 1375–1384 (2021)
Jian, H., Coleman, K., et al.: Deciphering tumor ecosystems at super resolution from spatial transcriptomics with tesla. Cell Syst. 14(5), 404–417 (2023)
Zhang, D., Schroeder, A., et al.: Inferring super-resolution tissue architecture by integrating spatial transcriptomics with histology. Nat. Biotechnol. 1–6 (2024). https://doi.org/10.1038/s41587-023-02019-9
Andersson, A., Lundeberg, J.: sepal: identifying transcript profiles with spatial patterns by diffusion-based modeling. Bioinformatics 37(17), 2644–2650 (2021)
Raudvere, U., Kolberg, L., et al.: g: Profiler: a web server for functional enrichment analysis and conversions of gene lists (2019 update). Nucleic Acids Res. 47(W1), W191–W198 (2019)
Acknowledgements
The work was supported in part by the National Natural Science Foundation of China (No. 62262069), in part by the Yunnan Fundamental Research Projects under Grants (202201AT070469, 202301BF070001-019) and the Yunnan Talent Development Program - Youth Talent Project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xue, S., Zhu, F., Wang, C., Min, W. (2024). stEnTrans: Transformer-Based Deep Learning for Spatial Transcriptomics Enhancement. In: Peng, W., Cai, Z., Skums, P. (eds) Bioinformatics Research and Applications. ISBRA 2024. Lecture Notes in Computer Science(), vol 14954. Springer, Singapore. https://doi.org/10.1007/978-981-97-5128-0_6
Download citation
DOI: https://doi.org/10.1007/978-981-97-5128-0_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5127-3
Online ISBN: 978-981-97-5128-0
eBook Packages: Computer ScienceComputer Science (R0)