Aug 2026· Omics· pp.
15578100261480770
· 0 citations· 28 references
Medicine
TL;DR
A novel method of multimodal spatial omics fusion, named mmspao, is proposed to obtain cross-modal interactive features and combine them with the features of each modality to obtain fusion results at the spatial resolution.
Abstract
Multimodal spatial omics integration offers a powerful paradigm to decipher the hierarchical regulatory mechanisms underlying cellular function and tissue architecture. In this study, a novel method of multimodal spatial omics fusion, named mmspao, is proposed to obtain cross-modal interactive features and combine them with the features of each modality to obtain fusion results at the spatial resolution. This method integrates the data of spatial transcriptomics, epigenomics, and proteomics. It further integrates information from each modality using adjacency graph modeling and latent spatial representation. We demonstrate the effectiveness of this method on simulated and real multiomics data. By leveraging adjacency graph modeling and latent spatial representation, mmspao effectively aligns multiomics modalities within shared spatial domains, preserving individual gene expression profiles while generating globally integrated fusion maps that advance the decoding of tissue architecture and cellular regulatory hierarchies.
Spatial multi-omics technologies facilitate simultaneous measurement of multiple molecular modalities within their native spatial context, offering opportunities to characterize tissue organization and cellular heterogeneity, and SpaHDSRL, a hierarchical dual-graph self-supervised representation learning framework for...
Xiang Li, Kang-Kang Zhang, Yi-Fei Li et al.· Briefings in Bioinformatics· 0 citations
ILR-SMO (Iterative Latent Refinement for Spatial Multi-Omics) is proposed, a unified self-supervised framework that reformulates multimodal integration as a stability-aware refinement process over a shared latent representation, resulting in more stable and robust representation learning under heterogeneous and noisy m...
An-Qi Yu, Xu-Dong Xu, Jian-Zhi Lu et al.· Proceedings of the Thirty-Fi...· 0 citations
This study takes Leiden clustering as a reproducible baseline, carries out 72 groups of parameter evaluations on MouseBrain and HumanTonsil datasets, and systematically compares the effects of PCA dimension, neighbour number k and resolution on clustering granularity, consistency with reference labels and spatial conti...
Lin-Na Fan· Applied and Computational En...· 0 citations
A novel Biologically Interpretable multi-modal Graph using Spatial Transcriptomics, called BIGraph-ST, that integrates pathway activity scores and histological image features for robust spatial domain identification and provides biologically interpretable pathway-level representations of domains, which ultimately offer...
Seungeun Lee, Guolon Wang, Kyungtae Kang et al.· bioRxiv· 0 citations
Across multiple tissues, molecular modalities, developmental stages, sequencing platforms, and degraded datasets, SpatialMOC consistently outper-formed existing computational approaches in bidirectional molecular prediction and establishes SpatialMOC as a general framework for spatial multi-omics reconstruction.
Zhengxuan Liu, Peimeng Zhen, Bingtao Wang et al.· bioRxiv· 0 citations
