SpatialJEPA: JEPA-inspired graph-context distillation for spatially aware multiomics integration
Mann-Krzisnik, D.; Li, Y.
Show abstract
Computational frameworks for integrating spatial genomics modalities extend cell-based representation learning across molecular layers, but many paired RNA-ATAC datasets are dissociated and lack spatial coordinates. We introduce SpatialJEPA, a JEPA-inspired teacher-student framework for transferring spatial context from spatial multiomics data to non-spatial multiome data. In contrast to patch- or feature-masking objectives, SpatialJEPA masks spatial context by replacing the teachers spatial neighborhood graph with a self-only identity graph during student training, making the spatial sample appear dissociated to the student. The student learns to match teacher embeddings from this graph-context-restricted view and can therefore be applied to dissociated RNA-ATAC data at inference time. In mouse brain multiomics, the resulting representation supports source-target alignment, recovers spatially organized transcriptomic and chromatin-accessibility programs, and shows concordance with ligand-receptor pathway structure compared with non-spatial references.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- scMODAL: A general deep learning framework for comprehensive single-cell multi-omics data alignment with feature links 97%
- uniPort: a unified computational framework for single-cell data integration with optimal transport 96%
- Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data 96%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.