Inferring predictive genetic models and regulatory elements by deep learning of cross-species single-cell gene expression landscapes

Abstract

Despite extensive efforts to sequence different genomes, genetic models to interpret gene regulation and cell fate decisions are lacking for most species. Here, we performed whole-body single-cell transcriptomic analysis of zebrafish, Drosophila, and earthworm. We then mapped cell landscapes covering eight representative metazoan species to study gene regulation through evolution. With uniformly constructed cross-species datasets, we developed a deep learning-based strategy, Nvwa, to predict gene expression landscapes and decipher cis-regulatory elements (CREs) at the single-cell level. We systematically compared cell type-specific transcription factors (TFs) and CREs to reveal conserved genetic regulation among vertebrates and invertebrates. Our work provides a valuable resource and a novel strategy for studying regulatory language in diverse biological systems.

Systematic identification of cell-fate regulatory programs using a single-cell atlas of mouse development

“…First, we performed a comparative analysis of gene regulation during development in seven species with varying evolutionary distances at single-cell resolution. Development atlases of four invertebrates and three vertebrates were involved, including Schmidtea mediterranea 12 , Caenorhabditis elegan 15 , Ciona intestinalis 16 , Hydra vulgaris 13 , Danio rerio 42 , Mus musculus 11 , and Homo sapiens 14 . More than 1,100,000 cells were collected and categorized into 665 cell type pairs for relatively differentiated states and undifferentiated states (Extended Data Fig.…”