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 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 2 Mb away in the genome, GraphReg more faithfully models gene regulation and more accurately predicts gene expression levels than the 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 convolutional neural networks (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.

中文翻译：

---

图注意网络的染色质相互作用感知基因调控建模

将远端增强子与基因联系起来并模拟它们对靶基因表达的影响是调控基因组学中长期未解决的问题，对于解释非编码遗传变异至关重要。在这里，我们提出了一种新的深度学习方法，称为 GraphReg，它利用来自染色体构象捕获分析的 3D 相互作用来预测来自 1D 表观基因组数据或基因组 DNA 序列的基因表达。通过使用图注意力网络来利用基因组中最远 2 Mb 的远端元素的连接性，GraphReg 比用于该任务的最先进的深度学习方法更忠实地模拟基因调控并更准确地预测基因表达水平。与 GraphReg 一起使用的特征归因准确识别基因的功能增强子，经 CRISPRi-FlowFISH 和 TAP-seq 分析验证，优于卷积神经网络（CNN）和最近提出的接触活动模型。基于序列的 GraphReg 还通过 CRISPRi TF 敲除实验通过 TF 结合基序的计算机消融准确预测直接转录因子 (TF) 靶标。因此，GraphReg 代表了在模拟表观基因组和序列元素的调节影响方面取得的重要进展。