Chromatin interaction–aware gene regulatory modeling with graph attention networks

Abstract

Linking distal enhancers to genes and modeling their impact on target gene expression are longstanding unresolved problems in regulatory genomics and critical for interpreting noncoding genetic variation. Here we present a new deep learning approach called GraphReg that exploits 3D interactions from chromosome conformation capture assays in order to predict gene expression from 1D epigenomic data or genomic DNA sequence. By using graph attention networks to exploit the connectivity of distal elements up to 2Mb away in the genome, GraphReg more faithfully models gene regulation and more accurately predicts gene expression levels than state-of-the-art deep learning methods for this task. Feature attribution used with GraphReg accurately identifies functional enhancers of genes, as validated by CRISPRi-FlowFISH and TAP-seq assays, outperforming both CNNs and the recently proposed Activity-by-Contact model. Sequence-based GraphReg also accurately predicts direct transcription factor (TF) targets as validated by CRISPRi TF knockout experiments via in silico ablation of TF binding motifs. GraphReg therefore represents an important advance in modeling the regulatory impact of epigenomic and sequence elements.

Applications of deep learning in understanding gene regulation

“…Furthermore, Orca’s sequence encoder is simultaneously trained on the DHS and histone modification profiles of the two cell lines from ENCODE and Roadmap Epigenomics, making it an integrative and multi-purpose model. In contrast to the earlier works that have focused on sequence-based prediction of genome-folding maps, a recent model, GraphReg, 57 instead utilized the 3D structure of the genome for better prediction of gene expression levels. GraphReg contains a set of two models, Epi-GraphReg and Seq-GraphReg.…”

An encyclopedia of enhancer-gene regulatory interactions in the human genome

“…Toward this goal, the ENCODE Project has conducted thousands of experiments to identify candidate cis-regulatory elements and annotate their chromatin state and 3D physical interactions across hundreds of cell types and tissues 7 . Using these and other data, various predictive models have been developed and applied to identify enhancer-gene regulatory interactions [8][9][10][11][12][13][14][15][16] . Despite recent progress, key challenges remain.…”

“…Many previous efforts are missing information on the accuracy of predictions, have not been systematically compared to others using a common set of benchmarks, and/or have known limitations in prediction accuracy 6,[8][9][10][11][12]16,17 . We need larger sets of genetic perturbation data and a community framework to evaluate, compare, and develop improved predictive models of enhancer-gene regulatory interactions.…”

GILoop: Robust chromatin loop calling across multiple sequencing depths on Hi-C data

“… 15 , 16 , 17 , 18 Besides, in the latest studies, Hi-C graph has also been leveraged for modeling gene regulation patterns and predicting gene expression levels. 19 Another commonly adopted representation of Hi-C data mainly focuses on the 2D features of the cis -contact matrix. The linear connectivity of genomic loci enables the interaction matrix to manifest visually recognizable patterns on a grid-like 2D coordinate system, and thus it can be treated as an image.…”