Subspace Tensor Orthogonal Rotation Model (STORM) for Batch Alignment, Cell Type Deconvolution, and Gene Imputation in Spatial Transcriptomic Data

TL;DR

This paper introduces STORM, a novel interpretable tensor model that effectively aligns, deconvolves, and imputes spatial transcriptomics data, addressing batch effects and mixed cell signals with state-of-the-art results.

Contribution

STORM is a new tensor-based model that aligns spatial transcriptomics slices and performs cell-type deconvolution and gene imputation with interpretability.

Findings

Achieves state-of-the-art batch integration performance.

Effectively deconvolves cell types in spatial data.

Accurately imputes missing gene expression values.

Abstract

Spatial transcriptomics data analysis integrates cellular transcriptional activity with spatial coordinates to identify spatial domains, infer cell-type dynamics, and characterize gene expression patterns within tissues. Despite recent advances, significant challenges remain, including the treatment of batch effects, the handling of mixed cell-type signals, and the imputation of poorly measured or missing gene expression. This work addresses these challenges by introducing a novel Subspace Tensor Orthogonal Rotation Model (STORM) that aligns multiple slices which vary in their spatial dimensions and geometry by considering them at the level of physical patterns or microenvironments. To this end, STORM presents an irregular tensor factorization technique for decomposing a collection of gene expression matrices and integrating them into a shared latent space for downstream analysis. In contrast to black-box deep learning approaches, the proposed model is inherently interpretable. Numerical experiments demonstrate state-of-the-art performance in vertical and horizontal batch integration, cell-type deconvolution, and unmeasured gene imputation for spatial transcriptomics data.