Related Experiment Video
Updated: Aug 5, 2026
10:46
Dissection of Enhancer Function Using Multiplex CRISPR-based Enhancer Interference in Cell Lines
Published on: June 2, 2018
Mapping enhancer-gene regulatory interactions from single-cell data
Maya U Sheth1,2,3,4, Wei-Lin Qiu1,5, X Rosa Ma2,3
1The Novo Nordisk Foundation Center for Genomic Mechanisms of Disease, Broad Institute of MIT and Harvard, Cambridge, MA, USA.
Nature Genetics
|August 3, 2026
Summary
We developed scE2G, a new computational model to predict enhancer-gene regulatory interactions from single-cell data. This tool accurately maps gene regulation, aiding in understanding complex traits and human disease genetics.
Area of Science:
- Genomics
- Computational Biology
- Molecular Biology
Background:
- Accurate mapping of enhancer-gene regulatory interactions is vital for understanding gene regulation and human disease genetics.
- Predicting these interactions from single-cell datasets remains a significant challenge in the field.
Purpose of the Study:
- To introduce scE2G, a novel family of classification models designed to predict enhancer-gene regulatory interactions.
- To enable accurate mapping of these interactions across diverse human cell types.
Main Methods:
- Utilized single-cell assay for transposase-accessible chromatin with sequencing (scATAC-seq) and multiomic RNA and ATAC-seq data.
- Trained models on a large CRISPR perturbation dataset (>10,000 element-gene pairs).
- Benchmarked scE2G against CRISPR perturbations, fine-mapped eQTLs, and GWAS variant-gene associations.
Main Results:
- Demonstrated state-of-the-art performance in predicting enhancer-gene interactions across various cell types and perturbation categories.
- Successfully applied scE2G to map regulatory interactions in heterogeneous tissues.
- Identified potential regulatory interactions linking INPP4B and IL15 to lymphocyte count.
Conclusions:
- scE2G models offer a powerful and accurate approach for predicting enhancer-gene regulatory interactions.
- This methodology facilitates the interpretation of noncoding variants associated with complex traits.
- The developed models will significantly advance the mapping of enhancer-gene regulatory networks in thousands of human cell types.
