The interpretable multimodal dimension reduction framework SpaHDmap enhances resolution in spatial transcriptomics

作者：Junjie Tang, Zihao Chen, Kun Qian, Siyuan Huang, Y. He, Shenyi Yin, Xinyu He, Buqing Ye, YAN ZHUANG, Hongxue Meng, J B Xi, Ruibin Xi · 发表于：Nature Cell Biology · 年份：2026 · DOI：10.1038/s41556-025-01838-z · 被引用次数：7 · 研究领域：Single-cell and spatial transcriptomics、Gene expression and cancer classification、Domain Adaptation and Few-Shot Learning

Spatial transcriptomics (ST) technologies revolutionized tissue architecture studies by capturing gene expression with spatial context. However, high-dimensional ST data often have limited spatial resolution and exhibit considerable noise and sparsity, posing substantial challenges in deciphering subtle spatial structures and underlying biological activities. Here we introduce 'spatial high-definition embedding mapping' (SpaHDmap), an interpretable dimension reduction framework that enhances spatial resolution by integrating ST gene expression with high-resolution histology images. SpaHDmap incorporates non-negative matrix factorization into a deep learning framework, enabling the identification of high-resolution spatial metagenes (embeddings). Furthermore, SpaHDmap can simultaneously analyse multiple samples and is compatible with various types of histology images. Extensive evaluations on synthetic, public and newly sequenced ST datasets from various technologies and tissue types demonstrate that SpaHDmap can effectively produce high-resolution spatial metagenes, and detect refined spatial structures. SpaHDmap represents a powerful approach for integrating ST data and histology images, offering deeper insights into complex tissue structures and functions.