scSpecies: enhancement of network architecture alignment in comparative single-cell studies

Animals can provide meaningful context for human single-cell data. To transfer information between species, we propose a deep learning approach that pre-trains a conditional variational autoencoder on animal data and transfers its final encoder layers to a human network architecture. Our approach then aligns latent spaces by leveraging data-level and model-learned similarities. We utilize this for label transfer and differential gene expression analysis in cross-species pairs of liver, adipose tissue, and glioblastoma datasets. Our results are robust even when gene sets differ, or datasets are small. Thus, we reliably exploit similarities between species to provide context for human single-cell data.