近日，美国普林斯顿大学Benjamin J. Raphael及其研究团队，通过可解释深度学习绘制空间基因表达的拓扑图。2025年1月23日，《自然—方法学》杂志在线发表了这项成果。

据研究人员介绍，空间分辨转录组学技术提供了组织切片中基因表达的高通量测量，但这些数据的稀疏性使得空间基因表达模式的分析变得复杂。

研究人员通过使用一种称为等深度（isodepth）的量来解决这一问题，从而得出组织切片的拓扑图——类似于地形图中的高程图。等深度的等高线包围了具有不同细胞类型组成的区域，而等深度的梯度则指示了表达变化的最大空间方向。

研究人员开发了GASTON（通过神经网络分析空间转录组学组织的梯度），这是一种无监督且可解释的深度学习算法，能够同时学习等深度、空间梯度和分段线性表达函数，后者模拟了基因表达中连续梯度和不连续变化的模式。研究人员展示了GASTON能够准确识别多个组织中的空间区域和标记基因、大脑中的神经分化和放电梯度，以及肿瘤微环境中代谢和免疫活动的梯度。

附：英文原文

Title: Mapping the topography of spatial gene expression with interpretable deep learning

Author: Chitra, Uthsav, Arnold, Brian J., Sarkar, Hirak, Sanno, Kohei, Ma, Cong, Lopez-Darwin, Sereno, Raphael, Benjamin J.

Issue&Volume: 2025-01-23

Abstract: Spatially resolved transcriptomics technologies provide high-throughput measurements of gene expression in a tissue slice, but the sparsity of these data complicates analysis of spatial gene expression patterns. We address this issue by deriving a topographic map of a tissue slice—analogous to a map of elevation in a landscape—using a quantity called the isodepth. Contours of constant isodepths enclose domains with distinct cell type composition, while gradients of the isodepth indicate spatial directions of maximum change in expression. We develop GASTON (gradient analysis of spatial transcriptomics organization with neural networks), an unsupervised and interpretable deep learning algorithm that simultaneously learns the isodepth, spatial gradients and piecewise linear expression functions that model both continuous gradients and discontinuous variation in gene expression. We show that GASTON accurately identifies spatial domains and marker genes across several tissues, gradients of neuronal differentiation and firing in the brain, and gradients of metabolism and immune activity in the tumor microenvironment.

DOI: 10.1038/s41592-024-02503-3

Source: https://www.nature.com/articles/s41592-024-02503-3