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

ABSTRACT:

Motivation

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.

Results

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 t

SUBMITTER: Hu Y 

PROVIDER: S-EPMC8382278 | biostudies-literature | 2021 Jul

REPOSITORIES: biostudies-literature