Chromatin interaction-aware gene regulatory modeling with graph attention networks.
Chromatin interaction-aware gene regulatory modeling with graph attention networks.
复制标题
DOI：
10.1101/gr.275870.121
复制
发表时间：
2022-05
期刊：
影响因子：
7
通讯作者：
Leslie CS
中科院分区：
文献类型：
--
作者：
Karbalayghareh A;Sahin M;Leslie CS
将远端增强子连接到基因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交互作用来预测来自一维表观基因组数据或基因组DNA序列的基因表达。通过使用图形注意网络来利用基因组中远至2Mb的末端元件的连通性，GraphReg比这项任务的最先进的深度学习方法更真实地模拟基因调控并更准确地预测基因表达水平。通过CRISPRi-FlowFISH和TAP-SEQ分析验证，GraphReg使用的特征属性准确地识别了基因的功能增强子，表现优于卷积神经网络(CNN)和最近提出的按接触活动模型。基于序列的GraphReg还可以准确地预测直接转录因子(TF)的靶标，这一点已经通过电子消融直接转录因子结合基序的CRISPRi TF敲除实验得到了验证。因此，GraphReg代表了在对表观基因组和序列元件的调控影响进行建模方面的重要进展。
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.
登录
查看更多内容
DOI：
10.1093/bioinformatics/btr064
发表时间：
2011-04-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Grant CE;Bailey TL;Noble WS
通讯作者：
Noble WS
影响因子：
8.8
作者：
Agarwal, Vikram;Shendure, Jay
通讯作者：
Shendure, Jay
影响因子：
30.8
作者：
Fulco, Charles P.;Nasser, Joseph;Engreitz, Jesse M.
通讯作者：
Engreitz, Jesse M.
影响因子：
30.8
作者：
González AJ;Setty M;Leslie CS
通讯作者：
Leslie CS
影响因子：
5.8
作者：
Singh, Ritambhara;Lanchantin, Jack;Qi, Yanjun
通讯作者：
Qi, Yanjun