Cross-Propagative Graph Learning Reveals Spatial Tissue Domains in Multi-Modal Spatial Transcriptomics
Guo, Y.; Liu, S.; Zhang, Z.; Zhang, S.; Li, L.
Show abstract
Spatial transcriptomics enables in situ characterization of tissue organization by jointly profiling gene expression profiles and spatial coordinates, with histological images as complementary contextual information. However, effectively integrating these heterogeneous modalities remains challenging due to differences in statistical properties and structural patterns. We propose st-Xprop, a cross-propagative graph network with dual-graph embedding coupling for spatial domain identification. st-Xprop constructs modality-specific graphs for gene expression and histological features, and performs alternating cross-modal propagation to explicitly model inter-modal heterogeneity while enabling complementary information exchange. Through dual-graph embedding coupling, the framework progressively learns a unified low-dimensional representation that integrates multimodal signals and preserves spatial coherence. Evaluations on multiple real spatial transcriptomics datasets demonstrate that st-Xprop consistently improves clustering accuracy and robustness, particularly in weak-signal or structurally complex regions, yielding spatial domains that are more stable and biologically meaningful.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Probabilistic embedding, clustering, and alignment for integrating spatial transcriptomics data with PRECAST 98%
- Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with GraphST 97%
- uniPort: a unified computational framework for single-cell data integration with optimal transport 97%
Similar papers in this journal
- Predicting MammaPrint Recurrence Risk from Breast Cancer Pathological Images Using a Weakly Supervised Transformer 94%
- Information-Distilled Generative Label-Free Morphological Profiling Encodes Cellular Heterogeneity 94%
- DeDoc2 identifies and characterizes the hierarchy and dynamics of chromatin TAD-like domains in the single cells 93%
Similar papers in this journal
- stGCL: A versatile cross-modality fusion method based on multi-modal graph contrastive learning for spatial transcriptomics 96%
- stDyer enables spatial domain clustering with dynamic graph embedding 96%
- scCross: A Deep Generative Model for Unifying Single-cell Multi-omics with Seamless Integration, Cross-modal Generation, and In-silico Exploration 96%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.