BreakNet: detecting deletions using long reads and a deep learning approach

Structural variations (SVs) occupy a prominent position in human genetic diversity, and deletions form an important type of SV that has been suggested to be associated with genetic diseases. Although various deletion calling methods based on long reads have been proposed, a new approach is still nee...

Full description

Saved in:
Bibliographic Details
Published in:BMC bioinformatics 2021-12, Vol.22 (1), p.1-577, Article 577
Main Authors: Luo, Junwei, Ding, Hongyu, Shen, Jiquan, Zhai, Haixia, Wu, Zhengjiang, Yan, Chaokun, Luo, Huimin
Format: Article
Language:English
Subjects:
Analysis
Artificial neural networks
Care and treatment
Cigars
Deep learning
Diagnosis
Feature extraction
Gene deletion
Genetic disorders
Genetic diversity
Genomes
Genomic structural variations
Long short-term memory
Machine learning
Mathematical analysis
Methods
Neural networks
Parameter estimation
Risk factors
Source code
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Structural variations (SVs) occupy a prominent position in human genetic diversity, and deletions form an important type of SV that has been suggested to be associated with genetic diseases. Although various deletion calling methods based on long reads have been proposed, a new approach is still needed to mine features in long-read alignment information. Recently, deep learning has attracted much attention in genome analysis, and it is a promising technique for calling SVs. In this paper, we propose BreakNet, a deep learning method that detects deletions by using long reads. BreakNet first extracts feature matrices from long-read alignments. Second, it uses a time-distributed convolutional neural network (CNN) to integrate and map the feature matrices to feature vectors. Third, BreakNet employs a bidirectional long short-term memory (BLSTM) model to analyse the produced set of continuous feature vectors in both the forward and backward directions. Finally, a classification module determines whether a region refers to a deletion. On real long-read sequencing datasets, we demonstrate that BreakNet outperforms Sniffles, SVIM and cuteSV in terms of their F1 scores. The source code for the proposed method is available from GitHub at https://github.com/luojunwei/BreakNet. Our work shows that deep learning can be combined with long reads to call deletions more effectively than existing methods.
ISSN:1471-2105
1471-2105
DOI:10.1186/s12859-021-04499-5