DeepPHiC: predicting promoter-centered chromatin interactions using a novel deep learning approach.
DeepPHiC: predicting promoter-centered chromatin interactions using a novel deep learning approach.
复制标题
DOI：
10.1093/bioinformatics/btac801
复制
发表时间：
2023-01-01
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
以启动子为中心的染色质相互作用，包括启动子-增强子（PE）和启动子-启动子（PP）相互作用，对于破译基因调控和疾病机制非常重要。下一代测序技术如启动子捕获Hi-C（pcHi-C）的发展导致了以启动子为中心的染色质相互作用的发现。然而，pcHi-C实验是昂贵的，因此可能无法用于感兴趣的组织/细胞类型。此外，这些实验可能由于测序深度不足或各种伪影而动力不足，这导致相互作用的发现有限。大多数现有的用于预测染色质相互作用的计算方法是基于原位Hi-C，并且可以检测整个基因组中的染色质相互作用。然而，他们可能不是最佳的预测启动子为中心的染色质相互作用。我们开发了一个监督多模态深度学习模型，该模型利用一组全面的特征，如基因组序列，表观遗传信号，锚距离，进化特征和DNA结构特征来预测组织/细胞类型特异性PE和PP相互作用。我们进一步扩展了多任务学习和迁移学习框架中的深度学习模型，并证明了所提出的方法优于最先进的深度学习方法。此外，与在预训练中使用所有组织/细胞类型相比，所提出的方法可以使用预定义的生物相关组织/细胞类型实现相当的预测性能，特别是用于预测PE相互作用。通过在预训练中使用计算推断的生物学相关组织/细胞类型可以进一步提高预测性能，所述生物学相关组织/细胞类型是基于染色质相互作用中两个锚附近的共同基因定义的。 https://github.com/lichen-lab/DeepPHiC. 补充数据可在Bioinformatics在线获得。
Promoter-centered chromatin interactions, which include promoter–enhancer (PE) and promoter–promoter (PP) interactions, are important to decipher gene regulation and disease mechanisms. The development of next-generation sequencing technologies such as promoter capture Hi-C (pcHi-C) leads to the discovery of promoter-centered chromatin interactions. However, pcHi-C experiments are expensive and thus may be unavailable for tissues/cell types of interest. In addition, these experiments may be underpowered due to insufficient sequencing depth or various artifacts, which results in a limited finding of interactions. Most existing computational methods for predicting chromatin interactions are based on in situ Hi-C and can detect chromatin interactions across the entire genome. However, they may not be optimal for predicting promoter-centered chromatin interactions. We develop a supervised multi-modal deep learning model, which utilizes a comprehensive set of features such as genomic sequence, epigenetic signal, anchor distance, evolutionary features and DNA structural features to predict tissue/cell type-specific PE and PP interactions. We further extend the deep learning model in a multi-task learning and a transfer learning framework and demonstrate that the proposed approach outperforms state-of-the-art deep learning methods. Moreover, the proposed approach can achieve comparable prediction performance using predefined biologically relevant tissues/cell types compared to using all tissues/cell types in the pretraining especially for predicting PE interactions. The prediction performance can be further improved by using computationally inferred biologically relevant tissues/cell types in the pretraining, which are defined based on the common genes in the proximity of two anchors in the chromatin interactions. https://github.com/lichen-lab/DeepPHiC. Supplementary data are available at Bioinformatics online.
登录
查看更多内容
影响因子：
64.8
作者：
Jin, Fulai;Li, Yan;Dixon, Jesse R.;Selvaraj, Siddarth;Ye, Zhen;Lee, Ah Young;Yen, Chia-An;Schmitt, Anthony D.;Espinoza, Celso A.;Ren, Bing
通讯作者：
Ren, Bing
影响因子：
64.8
作者：
通讯作者：
--
DeepTACT：通过引导深度学习预测 3D 染色质接触
影响因子：
14.9
作者：
Li, Wenran;Wong, Wing Hung;Jiang, Rui
通讯作者：
Jiang, Rui
影响因子：
14.9
作者：
Yang D;Jang I;Choi J;Kim MS;Lee AJ;Kim H;Eom J;Kim D;Jung I;Lee B
通讯作者：
Lee B
影响因子：
5.8
作者：
Chen, Li;Wang, Ye;Zhao, Fengdi
通讯作者：
Zhao, Fengdi