MGCF-Net: a multi-view granular-ball contrastive fusion network for spatial transcriptomics clustering.
- 1Graduate School of Dalian Medical University, Dalian, Liaoning, China.
- 2State Key Laboratory of Frigid Zone Cardiovascular Disease, Department of Cardiovascular Surgery, General Hospital of Northern Theater Command, Shenyang, Liaoning, China.
- 3Postgraduate College, China Medical University, Shenyang, Liaoning, China.
Abstract
Introduction
Spatial domain identification from spatial transcriptomics (ST) data is essential for characterizing the spatial organization of complex tissues. Existing contrastive learning methods face a persistent trade-off: instance-level approaches are susceptible to false negatives, whereas cluster-level methods may overlook fine-grained local structures. Moreover, direct multi-view fusion may introduce redundant or noisy correlations, thereby degrading representation quality.Methods
To address these limitations, we propose MGCF-Net, a multi-view granular-ball contrastive fusion network for spatial domain identification. MGCF-Net constructs a spatial graph and a feature graph to represent physical proximity and transcriptomic similarity, respectively. A redundancy-reduction objective preserves spot-level correspondence across the two views while suppressing spurious similarities between different spots. Multi-view granular-ball contrastive learning groups spot-level representations into local structural units and aligns them across views according to their membership overlap.Results
On eight dorsolateral prefrontal cortex (DLPFC) tissue sections, MGCF-Net attains the highest mean adjusted Rand index (ARI) among the evaluated methods. Its normalized mutual information (NMI) remains competitive with the comparison methods.Discussion
By contrasting local structural units rather than individual spots, MGCF-Net reduces the influence of false negatives arising from instance-level contrastive learning. This group-level formulation preserves coherent spatial structures without requiring a generative decoder.
Related
- Comments on "SpatialDG: a novel spatial domain identification method for spatially resolved transcriptomics data based on dual-graph neural network".
- Spatial transcriptomics reveals microenvironmental heterogeneity in osteoarthritic subchondral bone
- 1170 Spatial transcriptomics identifies immune heterogeneity in estrogen receptor positive postpartum breast cancer
- stFormer integrates spatial ligand signaling into a foundation model for spatial transcriptomics
- Applying Spatial Transcriptomics to the Human Heart: A Practical Guide for Translational Studies.
BibTeX
@article{zhu2026mgcfnet,
title = {{MGCF-Net: a multi-view granular-ball contrastive fusion network for spatial transcriptomics clustering.}},
author = {Li Zhu and Haiyao Dong and Yuji Zhang and Yong Zhang and Xinyi Huang and Huishan Wang},
journal = {Frontiers in physiology},
year = {2026},
month = oct,
doi = {10.3389/fphys.2026.1967219},
url = {https://europepmc.org/article/MED/42908645},
note = {CC BY},
}
RIS
TY - JOUR
TI - MGCF-Net: a multi-view granular-ball contrastive fusion network for spatial transcriptomics clustering.
AU - Li Zhu
AU - Haiyao Dong
AU - Yuji Zhang
AU - Yong Zhang
AU - Xinyi Huang
AU - Huishan Wang
PY - 2026
DA - 2026/10/07
JO - Frontiers in physiology
DO - 10.3389/fphys.2026.1967219
UR - https://europepmc.org/article/MED/42908645
AB - Introduction Spatial domain identification from spatial transcriptomics (ST) data is essential for characterizing the spatial organization of complex tissues. Existing contrastive learning methods face a persistent trade-off: instance-level approaches are susceptible to false negatives, whereas cluster-level methods may overlook fine-grained local structures. Moreover, direct multi-view fusion may introduce redundant or noisy correlations, thereby degrading representation quality.Methods To address these limitations, we propose MGCF-Net, a multi-view granular-ball contrastive fusion network for spatial domain identification. MGCF-Net constructs a spatial graph and a feature graph to represent physical proximity and transcriptomic similarity, respectively. A redundancy-reduction objective preserves spot-level correspondence across the two views while suppressing spurious similarities between different spots. Multi-view granular-ball contrastive learning groups spot-level representations into local structural units and aligns them across views according to their membership overlap.Results On eight dorsolateral prefrontal cortex (DLPFC) tissue sections, MGCF-Net attains the highest mean adjusted Rand index (ARI) among the evaluated methods. Its normalized mutual information (NMI) remains competitive with the comparison methods.Discussion By contrasting local structural units rather than individual spots, MGCF-Net reduces the influence of false negatives arising from instance-level contrastive learning. This group-level formulation preserves coherent spatial structures without requiring a generative decoder.
SN - 1664-042X
ER -