Large-scale spatial variable gene atlas for spatial transcriptomics

2025-10-08

AI Summary

Spatially variable gene (SVG) detection methods in spatial transcriptomics lack systematic, cross-platform and cross-tissue benchmarking; moreover, no spatial gene program atlas supports cancer–normal tissue comparisons. Method: We developed STimage-1K4M—the first large-scale, multi-platform, cross-tissue (18+ tissue types) SVG evaluation framework—and systematically benchmarked 20 state-of-the-art SVG algorithms using multidimensional metrics: histopathology marker gene recovery, cross-section reproducibility, high-resolution scalability, and technical robustness. Contribution/Results: Based on this benchmark, we release the first cross-tissue SVG gene atlas, revealing expression commonalities among developmentally or functionally related tissues. We further identify key spatial gene programs associated with tumor metastasis, immune infiltration, and tissue of origin—providing a rigorously validated resource for mechanistic discovery and clinical translation.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Computer Vision: Medical and Biological Imaging
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Spatial variable genes (SVGs) reveal critical information about tissue architecture, cellular interactions, and disease microenvironments. As spatial transcriptomics (ST) technologies proliferate, accurately identifying SVGs across diverse platforms, tissue types, and disease contexts has become both a major opportunity and a significant computational challenge. Here, we present a comprehensive benchmarking study of 20 state-of-the-art SVG detection methods using human slides from STimage-1K4M, a large-scale resource of ST data comprising 662 slides from more than 18 tissue types. We evaluate each method across a range of biologically and technically meaningful criteria, including recovery of pathologist-annotated domain-specific markers, cross-slide reproducibility, scalability to high-resolution data, and robustness to technical variation. Our results reveal marked differences in performance depending on tissue type, spatial resolution, and study design. Beyond benchmarking, we construct the first cross-tissue atlas of SVGs, enabling comparative analysis of spatial gene programs across cancer and normal tissues. We observe similarities between pairs of tissues that reflect developmental and functional relationships, such as high overlap between thymus and lymph node, and uncover spatial gene programs associated with metastasis, immune infiltration, and tissue-of-origin identity in cancer. Together, our work defines a framework for evaluating and interpreting spatial gene expression and establishes a reference resource for the ST community.

Problem

• Benchmarking 20 SVG detection methods across diverse tissue types
• Evaluating performance on biological and technical criteria systematically
• Constructing cross-tissue SVG atlas for comparative spatial analysis

Innovation

• Benchmarked 20 SVG detection methods comprehensively
• Constructed first cross-tissue SVG atlas resource
• Established evaluation framework for spatial transcriptomics