.png){kind=icon}
Return
Spatially Resolved Transcriptomics Data Clustering With Modality Conflict Modulation
.png){kind=icon}
PRE
AI
DOI：10.1109/tetci.2026.3675463.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Spatial transcriptomics (ST) clustering identifies distinct spatial domains within tissues and elucidates cellular interactions. While this approach has advanced human understanding of cellular organization, ST data exhibit modality conflict between transcriptional profiles and spatial coordinates. This conflict manifests as spatial neighboring spots displaying expression divergence and presents fundamental challenges in defining cluster boundaries. To address this, we propose a spatially resolved transcriptomics data clustering network with modality conflict modulation(stMCM). Our framework is the first one that transforms cellular spatial coordinates into feature representations while introducing a novel cross-propagation architecture that propagates spatial and gene features through dual graph networks, thereby reinforcing consistency in domains where spatial and transcriptional patterns align. To specifically address spatial spurious correlations in cell pairs exhibiting expression divergence, we projected gene features onto a hypersphere to calculate similarity, followed by evaluation of spatially masked graph reconstruction likelihood using Jensen-Shannon Divergence (JSD). Extensive experimental results demonstrate that our approach surpasses existing state-of-the-art methods in clustering tasks and related downstream applications.
Keywords:
Spatial transcriptomics clustering
modality conflict
cross-propagation
spatial coordinates
Journal
I
IF:
6.5
Papers:
1.4K
Citations:
4.5K
Organization
Cited Papers
MAEST: accurately spatial domain detection in spatial transcriptomics with graph masked autoencoder
OAAI
OAAIShareSaveShareSaveShareSaveShareSaveShareSaveDeciphering cell-cell communication at single-cell resolution for spatial transcriptomics with subgraph-based graph attention network.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAIShareSaveShareSave
View more