Abstract
BackgroundThe DNase I hypersensitive sites (DHSs) are associated with the cis-regulatory DNA elements. An efficient method of identifying DHSs can enhance the understanding on the accessibility of chromatin. Despite a multitude of resources available on line including experimental datasets and computational tools, the complex language of DHSs remains incompletely understood.MethodsHere, we address this challenge using an approach based on a state-of-the-art machine learning method. We present a novel convolutional neural network (CNN) which combined Inception like networks with a gating mechanism for the response of multiple patterns and longterm association in DNA sequences to predict multi-scale DHSs in Arabidopsis, rice and Homo sapiens.ResultsOur method obtains 0.961 area under curve (AUC) on Arabidopsis, 0.969 AUC on rice and 0.918 AUC on Homo sapiens.ConclusionsOur method provides an efficient and accurate way to identify multi-scale DHSs sequences by deep learning.
Highlights
The DNase I hypersensitive sites (DHSs) are associated with the cis-regulatory DNA elements
Some other research [4, 5] have that many DHSs appear around the highly expressed genes, and few DHSs appear near the low-expressed genes
The experimental conclusions illustrate that convolutional neural network (CNN) network can effectively extract features from nucleotide sequences and be used for genome-wide DHSs classification
Summary
The DNase I hypersensitive sites (DHSs) are associated with the cis-regulatory DNA elements. Some research attempts that DHSs can be precisely coupled with the cis-regulatory elements, including enhancers, promoters, silencers, and locus control regions [3]. There have a single cell DNase I sequencing (scDNaseseq) [10] method that can identify genome-wide DHSs in a single cell type or less than 1000 cell types. These estimable experimental methods collected many valuable data. It contributes important suggestions for studying the activity of the DNase I, the accessibility of chromatin and gene expression.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have