MoRE-GNN: Multi-omics Data Integration with a Heterogeneous Graph Autoencoder
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909831129989120 |
|---|---|
| author | Wang, Zhiyu Koszut, Sonia Liò, Pietro Ceccarelli, Francesco |
| author_facet | Wang, Zhiyu Koszut, Sonia Liò, Pietro Ceccarelli, Francesco |
| contents | The integration of multi-omics single-cell data remains challenging due to high-dimensionality and complex inter-modality relationships. To address this, we introduce MoRE-GNN (Multi-omics Relational Edge Graph Neural Network), a heterogeneous graph autoencoder that combines graph convolution and attention mechanisms to dynamically construct relational graphs directly from data. Evaluations on six publicly available datasets demonstrate that MoRE-GNN captures biologically meaningful relationships and outperforms existing methods, particularly in settings with strong inter-modality correlations. Furthermore, the learned representations allow for accurate downstream cross-modal predictions. While performance may vary with dataset complexity, MoRE-GNN offers an adaptive, scalable and interpretable framework for advancing multi-omics integration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06880 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoRE-GNN: Multi-omics Data Integration with a Heterogeneous Graph Autoencoder Wang, Zhiyu Koszut, Sonia Liò, Pietro Ceccarelli, Francesco Machine Learning Artificial Intelligence The integration of multi-omics single-cell data remains challenging due to high-dimensionality and complex inter-modality relationships. To address this, we introduce MoRE-GNN (Multi-omics Relational Edge Graph Neural Network), a heterogeneous graph autoencoder that combines graph convolution and attention mechanisms to dynamically construct relational graphs directly from data. Evaluations on six publicly available datasets demonstrate that MoRE-GNN captures biologically meaningful relationships and outperforms existing methods, particularly in settings with strong inter-modality correlations. Furthermore, the learned representations allow for accurate downstream cross-modal predictions. While performance may vary with dataset complexity, MoRE-GNN offers an adaptive, scalable and interpretable framework for advancing multi-omics integration. |
| title | MoRE-GNN: Multi-omics Data Integration with a Heterogeneous Graph Autoencoder |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.06880 |