Enhancement of Network Architecture Alignment in Comparative Single-Cell Studies

Animal data can provide meaningful context for human gene expression at the single-cell level. This can improve cell-type detection and clarify how well animal models represent human biology. To achieve this, we propose a deep learning approach that identifies a unified latent space to map complex patterns between datasets. The proposed method is tested to facilitate information transfer in liver, adipose tissue, and glioblastoma datasets from various animal models. Our results are robust for small datasets and large differences in the observed gene sets. Thus, we reliably uncover and exploit similarities between species to provide context for human single-cell data.