Mapping enhancer-gene regulatory interactions from single-cell data.

scE2G models predict enhancer-gene interactions with over 80% accuracy across diverse human cell types, advancing understanding of gene regulation and disease genetics.

• Why it matters: Accurately mapping enhancer-gene interactions is essential for deciphering gene regulation and linking noncoding variants to complex traits, yet current methods face significant challenges.
• What they did: Researchers developed and trained scE2G classification models using single-cell ATAC-seq and multiomic data on over 10,000 element-gene pairs, benchmarking against CRISPR and GWAS data.
• The result: The models outperform existing approaches, enabling detailed maps of regulatory interactions in heterogeneous tissues and aiding interpretation of variants associated with traits like lymphocyte count.