SMOPCA: spatially aware dimension reduction integrating multi-omics improves the efficiency of spatial domain detection
Abstract Technological advances have enabled us to profile multiple omics layers with spatial information, significantly enhancing spatial domain detection and advancing a variety of biomedical research fields. Despite these advancements, there is a notable lack of effective methods for modeling spa...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-05-01
|
| Series: | Genome Biology |
| Online Access: | https://doi.org/10.1186/s13059-025-03576-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Technological advances have enabled us to profile multiple omics layers with spatial information, significantly enhancing spatial domain detection and advancing a variety of biomedical research fields. Despite these advancements, there is a notable lack of effective methods for modeling spatial multi-omics data. We introduce SMOPCA, a Spatial Multi-Omics Principal Component Analysis method designed to perform joint dimension reduction on multimodal data while preserving spatial dependencies. Extensive experiments reveal that SMOPCA outperforms existing single-modal and multimodal dimension reduction and clustering methods, across both single-cell and spatial multi-omics datasets derived from diverse technologies and tissue structures. |
|---|---|
| ISSN: | 1474-760X |