MATCHA: Probing multi-way chromatin interaction with hypergraph representation learning.

ABSTRACT: Recent advances in ligation-free, genome-wide chromatin interaction mapping such as SPRITE and ChIA-Drop have enabled the identification of simultaneous interactions involving multiple genomic loci within the same nuclei, which are informative to delineate higher-order genome organization and gene regulation mechanisms at single-nucleus resolution. Unfortunately, computational methods for analyzing multi-way chromatin interaction data are significantly underexplored. Here we develop an algorithm, called MATCHA, based on hypergraph representation learning where multi-way chromatin interactions are represented as hyperedges. Applications to SPRITE and ChIA-Drop data suggest that MATCHA is effective to denoise the data and make de novo predictions, which greatly enhances the data quali

SUBMITTER: Zhang R 

PROVIDER: S-EPMC7299183 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature