EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework.

EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework.
复制标题

DOI:
10.1093/bioinformatics/btab272
复制
发表时间:
2021-07-12
期刊:
Bioinformatics (Oxford, England)
影响因子:
--
通讯作者:
Ma W
Ma W
中科院分区:
其他
文献类型:
--
作者:
Hu Y;Ma W

文献摘要

参考文献

被引文献

相似文献

高通量染色体构象捕获 (Hi-C) 技术实现了染色质相互作用的全基因组图谱。然而,高分辨率 Hi-C 数据需要昂贵的深度测序;因此,仅在有限数量的细胞类型中实现了这一目标。基于神经网络的机器学习模型已经被开发出来作为解决这个问题的方法。在这项工作中,我们提出了一种新方法 EnHiC,用于基于生成对抗网络 (GAN) 框架从低分辨率输入数据预测高分辨率 Hi-C 矩阵。受非负矩阵分解的启发,我们的模型充分利用Hi-C矩阵的独特性质,从多尺度低分辨率矩阵中提取rank-1特征以提高分辨率。使用三个人类 Hi-C 数据集,我们证明 EnHiC 准确可靠地增强了 Hi-C 矩阵的分辨率,并且优于其他基于 GAN 的模型。此外,EnHiC 预测的高分辨率矩阵有助于准确检测拓扑相关域和精细尺度染色质相互作用。 EnHiC 可在 https://github.com/wmalab/EnHiC 上公开获取。 补充数据可在生物信息学在线获取。
The high-throughput chromosome conformation capture (Hi-C) technique has enabled genome-wide mapping of chromatin interactions. However, high-resolution Hi-C data requires costly, deep sequencing; therefore, it has only been achieved for a limited number of cell types. Machine learning models based on neural networks have been developed as a remedy to this problem. In this work, we propose a novel method, EnHiC, for predicting high-resolution Hi-C matrices from low-resolution input data based on a generative adversarial network (GAN) framework. Inspired by non-negative matrix factorization, our model fully exploits the unique properties of Hi-C matrices and extracts rank-1 features from multi-scale low-resolution matrices to enhance the resolution. Using three human Hi-C datasets, we demonstrated that EnHiC accurately and reliably enhanced the resolution of Hi-C matrices and outperformed other GAN-based models. Moreover, EnHiC-predicted high-resolution matrices facilitated the accurate detection of topologically associated domains and fine-scale chromatin interactions. EnHiC is publicly available at https://github.com/wmalab/EnHiC. Supplementary data are available at Bioinformatics online.
DOI: 10.1038/s41467-018-03113-2
发表时间: 2018-02-21
影响因子: 16.6
作者:
Zhang Y;An L;Xu J;Zhang B;Zheng WJ;Hu M;Tang J;Yue F
通讯作者: Yue F
DeepHiC:用于增强 Hi-C 数据分辨率的生成对抗网络
DOI: 10.1371/journal.pcbi.1007287
发表时间: 2020-02-01
影响因子: 4.3
作者:
Hong, Hao;Jiang, Shuai;Bo, Xiaochen
通讯作者: Bo, Xiaochen
DOI: 10.1093/bioinformatics/btz251
发表时间: 2019-11-01
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Liu, Tong;Wang, Zheng
通讯作者: Wang, Zheng
hicGAN 通过生成对抗网络推断超分辨率 Hi-C 数据
DOI: 10.1093/bioinformatics/btz317
发表时间: 2019-07-15
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Liu, Qiao;Lv, Hairong;Jiang, Rui
通讯作者: Jiang, Rui
DOI: 10.1093/nar/gkx644
发表时间: 2017-09-29
影响因子: 14.9
作者:
Kumar R;Sobhy H;Stenberg P;Lizana L
通讯作者: Lizana L