DeepSV: accurate calling of genomic deletions from high-throughput sequencing data using deep convolutional neural network

• Published in: BMC bioinformatics Vol. 20; no. 1; p. 665
• Main Authors: Cai, Lei, Wu, Yufeng, Gao, Jingyang
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 12.12.2019; BioMed Central; BMC
• Subjects: Analysis; Artificial intelligence; Artificial neural networks; Base Sequence; Cable television broadcasting industry; Chromosomes; Chromosomes, Human - genetics; Classification; Deep learning; Feature extraction; Gene sequencing; Genetic diversity; Genetic polymorphisms; Genetic research; Genetic variations; Genomes; Genomics; High-Throughput Nucleotide Sequencing; High-throughput sequencing; Humans; Machine Learning; Methods; Neural networks; Neural Networks, Computer; Next-generation sequencing; Novels; Nucleotides; Sequence Deletion; Signatures; Single nucleotide polymorphisms; Single-nucleotide polymorphism; Software; Structural variations; Training; Visualization; United States; Deep learning; Visualization; Feature extraction; Genetic variations; Structural variations; High-throughput sequencing
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-019-3299-y

Calling genetic variations from sequence reads is an important problem in genomics. There are many existing methods for calling various types of variations. Recently, Google developed a method for calling single nucleotide polymorphisms (SNPs) based on deep learning. Their method visualizes sequence reads in the forms of images. These images are then used to train a deep neural network model, which is used to call SNPs. This raises a research question: can deep learning be used to call more complex genetic variations such as structural variations (SVs) from sequence data? In this paper, we extend this high-level approach to the problem of calling structural variations. We present DeepSV, an approach based on deep learning for calling long deletions from sequence reads. DeepSV is based on a novel method of visualizing sequence reads. The visualization is designed to capture multiple sources of information in the sequence data that are relevant to long deletions. DeepSV also implements techniques for working with noisy training data. DeepSV trains a model from the visualized sequence reads and calls deletions based on this model. We demonstrate that DeepSV outperforms existing methods in terms of accuracy and efficiency of deletion calling on the data from the 1000 Genomes Project. Our work shows that deep learning can potentially lead to effective calling of different types of genetic variations that are complex than SNPs.