Related Experiment Video
Updated: Sep 22, 2026
Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection
Published on: July 6, 2022
AINR: attention-guided implicit neural representations for spatial domain identification in spatial transcriptomics
Yusen Zhang, Guodong Xiao, Ponian Li
1School of Mathematics and Statistics, Shandong University, Weihai, China.
Motivation:
Spatial transcriptomics measures gene expression together with spatial locations, but its data are noisy and sparse, and existing graph-based methods are complex and hard to scale.
Results:
We present AINR, an end-to-end deep learning framework that models spatial transcriptomics data as a geometrically constrained continuous biological field. AINR combines implicit neural representations with a spatially-aware attention mechanism and a total variation regularization term, using a periodic sine activation function to map spatial coordinates directly to gene expression while preserving spatial smoothness without explicit adjacency matrices. Across six diverse datasets, AINR consistently outperforms existing methods in spatial domain identification and remains robust even under extreme data sparsity.
Availability And Implementation:
The code for AINR is available at https://github.com/XGD1122/AINR.
