Epiphany: predicting Hi-C contact maps from 1D epigenomic signals.

Epiphany: predicting Hi-C contact maps from 1D epigenomic signals.
复制标题

DOI:
10.1186/s13059-023-02934-9
复制
发表时间:
2023-06-06
期刊:
影响因子:
12.3
通讯作者:
--
中科院分区:
生物学1区
文献类型:
--
作者:

文献摘要

参考文献

相似文献

最近的深度学习模型从DNA序列预测Hi-C接触图,实现了有希望的准确性,但无法推广到新的细胞类型,甚至无法捕捉训练细胞类型之间的差异。我们提出了Epiphany,一种神经网络,用于从广泛可用的表观基因组轨迹预测细胞类型特异性Hi-C接触图。Epiphany使用双向长短期记忆层来捕获长距离依赖关系,并可选地使用生成对抗网络架构来鼓励接触地图的真实性。主显节表现出良好的泛化,以保持出染色体内和跨细胞类型,产生准确的重复和相互作用的电话,并预测结构变化引起的扰动表观基因组信号。在线版本包含补充材料,可通过10.1186/s13059-023-02934-9获得。
Recent deep learning models that predict the Hi-C contact map from DNA sequence achieve promising accuracy but cannot generalize to new cell types and or even capture differences among training cell types. We propose Epiphany, a neural network to predict cell-type-specific Hi-C contact maps from widely available epigenomic tracks. Epiphany uses bidirectional long short-term memory layers to capture long-range dependencies and optionally a generative adversarial network architecture to encourage contact map realism. Epiphany shows excellent generalization to held-out chromosomes within and across cell types, yields accurate TAD and interaction calls, and predicts structural changes caused by perturbations of epigenomic signals. The online version contains supplementary material available at 10.1186/s13059-023-02934-9.
DOI: 10.1016/j.cels.2016.07.002
发表时间: 2016-07
期刊: Cell systems
影响因子: 9.3
作者:
Durand NC;Shamim MS;Machol I;Rao SS;Huntley MH;Lander ES;Aiden EL
通讯作者: Aiden EL
DOI: 10.1038/nature11243
发表时间: 2012-08-02
期刊: NATURE
影响因子: 64.8
作者:
Shen, Yin;Yue, Feng;McCleary, David F.;Ye, Zhen;Edsall, Lee;Kuan, Samantha;Wagner, Ulrich;Dixon, Jesse;Lee, Leonard;Lobanenkov, Victor V.;Ren, Bing
通讯作者: Ren, Bing
DOI: 10.1038/s41588-019-0466-z
发表时间: 2019-08-01
期刊: NATURE GENETICS
影响因子: 30.8
作者:
Despang, Alexandra;Schoepflin, Robert;Ibrahim, Daniel M.
通讯作者: Ibrahim, Daniel M.
DOI: 10.1093/bioinformatics/btab083
发表时间: 2021-02-04
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Ji, Yanrong;Zhou, Zhihan;Davuluri, Ramana, V
通讯作者: Davuluri, Ramana, V
DOI: 10.1038/nature08497
发表时间: 2009-11-05
期刊: Nature
影响因子: 64.8
作者:
通讯作者: --