Mapping enhancer-gene regulatory interactions from single-cell data DOI Open Access
Maya U. Sheth, Wei‐Lin Qiu, X. Rosa

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 24, 2024

Abstract Mapping enhancers and their target genes in specific cell types is crucial for understanding gene regulation human disease genetics. However, accurately predicting enhancer-gene regulatory interactions from single-cell datasets has been challenging. Here, we introduce a new family of classification models, scE2G, to predict regulation. These models use features ATAC-seq or multiomic RNA data are trained on CRISPR perturbation dataset including >10,000 evaluated element-gene pairs. We benchmark scE2G against perturbations, fine-mapped eQTLs, GWAS variant-gene associations demonstrate state-of-the-art performance at prediction tasks across multiple categories perturbations. apply build maps heterogeneous tissues interpret noncoding variants associated with complex traits, nominating linking INPP4B IL15 lymphocyte counts. The will enable accurate mapping thousands diverse types.

Language: Английский

Mapping enhancer-gene regulatory interactions from single-cell data DOI Open Access
Maya U. Sheth, Wei‐Lin Qiu, X. Rosa

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 24, 2024

Abstract Mapping enhancers and their target genes in specific cell types is crucial for understanding gene regulation human disease genetics. However, accurately predicting enhancer-gene regulatory interactions from single-cell datasets has been challenging. Here, we introduce a new family of classification models, scE2G, to predict regulation. These models use features ATAC-seq or multiomic RNA data are trained on CRISPR perturbation dataset including >10,000 evaluated element-gene pairs. We benchmark scE2G against perturbations, fine-mapped eQTLs, GWAS variant-gene associations demonstrate state-of-the-art performance at prediction tasks across multiple categories perturbations. apply build maps heterogeneous tissues interpret noncoding variants associated with complex traits, nominating linking INPP4B IL15 lymphocyte counts. The will enable accurate mapping thousands diverse types.

Language: Английский

Citations

1