A. Ali Heydari

scANNA is an interpretable deep learning model for scRNA-seq that uses neural attention to learn gene associations, enabling downstream analyses without retraining.

This paper reviews deep learning methods for spatial transcriptomics, highlighting challenges and opportunities in analyzing spatially-resolved gene expression data.

N-ACT is an interpretable deep learning model for automatic cell type identification that detects salient genes, outperforming conventional methods in accuracy and scalability.

ACTIVA generates realistic synthetic scRNA-seq data with cell-type identification, improving classifier performance and reducing training time compared to existing methods.

This paper reviews deep learning applications in single-cell omics, finding that while promising, DL models still lack biological interpretability and have not yet solved major challenges in the field.