hicGAN infers super resolution Hi-C data with generative adversarial networks

Abstract

Motivation Hi-C is a genome-wide technology for investigating 3D chromatin conformation by measuring physical contacts between pairs of genomic regions. The resolution of Hi-C data directly impacts the effectiveness and accuracy of downstream analysis such as identifying topologically associating domains (TADs) and meaningful chromatin loops. High resolution Hi-C data are valuable resources which implicate the relationship between 3D genome conformation and function, especially linking distal regulatory elements to their target genes. However, high resolution Hi-C data across various tissues and cell types are not always available due to the high sequencing cost. It is therefore indispensable to develop computational approaches for enhancing the resolution of Hi-C data. Results We proposed hicGAN, an open-sourced framework, for inferring high resolution Hi-C data from low resolution Hi-C data with generative adversarial networks (GANs). To the best of our knowledge, this is the first study to apply GANs to 3D genome analysis. We demonstrate that hicGAN effectively enhances the resolution of low resolution Hi-C data by generating matrices that are highly consistent with the original high resolution Hi-C matrices. A typical scenario of usage for our approach is to enhance low resolution Hi-C data in new cell types, especially where the high resolution Hi-C data are not available. Our study not only presents a novel approach for enhancing Hi-C data resolution, but also provides fascinating insights into disclosing complex mechanism underlying the formation of chromatin contacts. Availability and implementation We release hicGAN as an open-sourced software at https://github.com/kimmo1019/hicGAN. Supplementary information Supplementary data are available at Bioinformatics online.

HiCSR: a Hi-C super-resolution framework for producing highly realistic contact maps

“…This is caused by an objective function which prefers solutions that are the pixel-wise average of many possible solutions that lie on the plausible image manifold (Mathieu et al, 2016). To avoid blurred predictions, hicGAN (Liu Q. et al, 2019) and DeepHiC (Hong et al, 2019) were proposed. First, hicGAN replaced pixelwise loss functions with a purely adversarial loss.…”

A machine learning framework for the prediction of chromatin folding inDrosophilausing epigenetic features

“…The machine learning approaches used in these works include generalized linear models (Ibn-Salem & Andrade-Navarro, 2019), random forest (Bkhetan & Plewczynski, 2018;, other ensemble models (Whalen, Truty & Pollard, 2016), and neural networks: multi-layer perceptron , dense neural networks (Zeng, Wu & Jiang, 2018;Farré et al, 2018;Li, Wong & Jiang, 2019), convolutional neural networks (Schreiber et al, 2017), generative adversarial networks (Liu, Lv & Jiang, 2019), and recurrent neural networks (Cristescu et al, 2018;Singh et al, 2019;Gan, Li & Jiang, 2019).…”

Peer Review #1 of "A machine learning framework for the prediction of chromatin folding in Drosophila using epigenetic features (v0.1)"

“…The machine learning approaches used in these works include generalized linear models (Ibn-Salem and Andrade-Navarro, 2019), random forest (Bkhetan and Plewczynski, 2018;Gan et al, 2019b), other ensemble models (Whalen et al, 2016), and neural networks: multi-layer perceptron (Gan et al, 2019b), dense neural networks (Zeng et al, 2018;Farré et al, 2018;Li et al, 2019), convolutional neural networks (Schreiber et al, 2017), generative adversarial networks (Liu et al, 2019), and recurrent neural networks (Cristescu et al, 2018;Singh et al, 2019;Gan et al, 2019a).…”