Dai Shurui, Li Jiawei, Xia Zhiliang, Ou Jingfeng, Guo Yan, Jiang Limin, Tang Jijun
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, 518005 Guangdong, China.
Department of Public Health Sciences, University of Miami, Miami, FL 33136, United States.
NAR Genom Bioinform. 2025 Aug 27;7(3):lqaf109. doi: 10.1093/nargab/lqaf109. eCollection 2025 Sep.
Single-cell RNA sequencing (scRNA-seq) has significantly deepened our understanding of cellular heterogeneity and cell type interactions, providing insights into how cell populations adapt to environmental variability. However, its lack of spatial context limits intercellular analysis. Similarly, existing spatial transcriptomics (ST) data often lack single-cell resolution, restricting cellular mapping. To address these limitations, we introduce ST-deconv, a deep learning-based deconvolution model that integrates spatial information. ST-deconv leverages contrastive learning to enhance the spatial representation of adjacent spots, improving spatial relationship inference. It also employs domain-adversarial networks to improve generalization and deconvolution across diverse datasets. Moreover, ST-deconv can generate large-scale, high-resolution spatial transcriptomic data with cell type labels from single-cell input, facilitating the learning of spatial cell type composition. In benchmarking experiments, ST-deconv outperforms traditional methods, reducing the root mean square error (RMSE) by 13% to 60%, with an RMSE as low as 0.03 for high spatial correlation datasets and 0.07 for low spatial correlation datasets across different transcriptomic contexts. Reconstructing real tissue structure, a purity of 0.68 on mouse olfactory bulb (MOB) and a cell type correlation of 0.76 on human pancreatic ductal adenocarcinoma (PDAC) were achieved. These advancements make ST-deconv a powerful tool for enhancing spatial transcriptomics and downstream analyses of intercellular interactions.
单细胞RNA测序(scRNA-seq)显著加深了我们对细胞异质性和细胞类型相互作用的理解,为细胞群体如何适应环境变化提供了见解。然而,其缺乏空间背景限制了细胞间分析。同样,现有的空间转录组学(ST)数据往往缺乏单细胞分辨率,限制了细胞图谱绘制。为了解决这些局限性,我们引入了ST-deconv,这是一种基于深度学习的反卷积模型,它整合了空间信息。ST-deconv利用对比学习来增强相邻斑点的空间表示,改善空间关系推断。它还采用域对抗网络来提高跨不同数据集的泛化能力和反卷积能力。此外,ST-deconv可以从单细胞输入生成带有细胞类型标签的大规模、高分辨率空间转录组数据,便于学习空间细胞类型组成。在基准实验中,ST-deconv优于传统方法,将均方根误差(RMSE)降低了13%至60%,在不同转录组背景下,对于高空间相关性数据集,RMSE低至0.03,对于低空间相关性数据集,RMSE为0.07。在重建真实组织结构方面,在小鼠嗅球(MOB)上达到了0.68的纯度,在人类胰腺导管腺癌(PDAC)上达到了0.76的细胞类型相关性。这些进展使ST-deconv成为增强空间转录组学和细胞间相互作用下游分析的强大工具。