Graspot: A graph attention network for spatial transcriptomics data integration with optimal transport

Abstract

Spatial transcriptomics (ST) technologies enable the measurement of mRNA expression while simultaneously capturing spot locations. By integrating ST data, the 3D structure of a tissue can be reconstructed, yielding a comprehensive understanding of the tissues intricacies. Nevertheless, a computational challenge persists: how to remove batch effects while preserving genuine biological structure variations across ST data. To address this, we introduce Graspot, a graph attention network designed for spatial transcriptomics data integration with unbalanced optimal transport. Graspot adeptly harnesses both gene expression and spatial information to align common structures across multiple ST datasets. It embeds multiple ST datasets into a unified latent space, facilitating the partial alignment of spots from different slices. Demonstrating superior performance compared to existing methods on four real spatial transcriptomics datasets, Graspot excels in ST data integration, including tasks that require partial alignment. In particular, Graspot unveils subtle tumor microenvironment structures of breast cancer, and accurately aligns the spatio-temporal transcriptomics data to reconstruct human heart developmental processes. The code for Graspot is available at https://github.com/zhan009/Graspot.