GROVER: Graph-guided Representation of Omics and Vision with Expert Regulation for Adaptive Spatial Multi-omics Fusion

2025-11-13

AI Summary

This study addresses three key challenges in integrating spatial multi-omics data (transcriptomics, proteomics, epigenomics) with histopathological images: modality heterogeneity, resolution mismatch, and signal distortion induced by biological perturbations. To this end, we propose a graph-guided nonlinear embedding framework. Our method innovatively integrates a Kolmogorov–Arnold network-driven graph convolutional encoder, a spot-feature pair contrastive learning strategy, and a dynamic expert routing mechanism—enabling explicit cross-modal alignment optimization, on-demand modality selection, and robust noise suppression. Evaluated on real spatial omics datasets, the framework significantly enhances multi-modal representation consistency and biological interpretability, outperforming state-of-the-art methods in fusion performance. It establishes a novel paradigm for high-fidelity, interpretable modeling of disease tissues.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Effectively modeling multimodal spatial omics data is critical for understanding tissue complexity and underlying biological mechanisms. While spatial transcriptomics, proteomics, and epigenomics capture molecular features, they lack pathological morphological context. Integrating these omics with histopathological images is therefore essential for comprehensive disease tissue analysis. However, substantial heterogeneity across omics, imaging, and spatial modalities poses significant challenges. Naive fusion of semantically distinct sources often leads to ambiguous representations. Additionally, the resolution mismatch between high-resolution histology images and lower-resolution sequencing spots complicates spatial alignment. Biological perturbations during sample preparation further distort modality-specific signals, hindering accurate integration. To address these challenges, we propose Graph-guided Representation of Omics and Vision with Expert Regulation for Adaptive Spatial Multi-omics Fusion (GROVER), a novel framework for adaptive integration of spatial multi-omics data. GROVER leverages a Graph Convolutional Network encoder based on Kolmogorov-Arnold Networks to capture the nonlinear dependencies between each modality and its associated spatial structure, thereby producing expressive, modality-specific embeddings. To align these representations, we introduce a spot-feature-pair contrastive learning strategy that explicitly optimizes the correspondence across modalities at each spot. Furthermore, we design a dynamic expert routing mechanism that adaptively selects informative modalities for each spot while suppressing noisy or low-quality inputs. Experiments on real-world spatial omics datasets demonstrate that GROVER outperforms state-of-the-art baselines, providing a robust and reliable solution for multimodal integration.

Problem

• Integrating multimodal spatial omics data with histopathological images for comprehensive tissue analysis
• Addressing resolution mismatch between high-resolution images and lower-resolution sequencing spots
• Overcoming biological perturbations that distort modality-specific signals during integration

Innovation

• Graph Convolutional Network captures nonlinear spatial dependencies
• Spot-feature-pair contrastive learning aligns cross-modal correspondences
• Dynamic expert routing adaptively selects informative modalities