Cnngeno: A high-precision deep learning based strategy for the calling of structural variation genotype. (October 2021)

• Record Type: Journal Article
• Authors: Bai, Ruofei; Ling, Cheng; Cai, Lei; Gao, Jingyang
• Is Part Of: Computational biology and chemistry. Volume 94(2021)
• Publication Date: 2021-10
• Subjects: Genotype calling -- Structural variations -- Next-generation data -- Convolutional neural network -- Bootstrapping strategy; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2020.107417
• Languages: English
• ISSNs: 1476-9271

Abstract

Graphical abstract: This paper attempts to bridge this gap by proposing a new calling approach based on deep learning, namely Cnngeno. Cnngeno converts sequencing texts to their corresponding images and classifies the genotypes of the images by Convolutional Neural Network (CNN). Moreover, the convolutional bootstrapping algorithm is adopted, which greatly improves the anti-noisy label ability of the deep learning network on real data. Highlights: Cnngeno can convert sequencing data into images and classifies the genotypes from these images using the convolutional neural network(CNN). Cnngeno adopted the convolutional bootstrapping strategy to improve the anti-noisy label's ability. The results show that Cnngeno performs better in terms of precision for calling genotype when compared with other existing methods. Abstract: Genotype plays a significant role in determining characteristics in an organism and genotype calling has been greatly accelerated by sequencing technologies. Furthermore, most parametric statistical models are unable to effectively call genotype, which is influenced by the size of structural variations and the coverage fluctuations of sequencing data. In this study, we propose a new method for calling deletions' genotypes from the next-generation data, called Cnngeno. Cnngeno can convert sequencing data into images and classifies the genotypes from these images using the convolutional neural network(CNN). Moreover, Cnngeno adopted the convolutional bootstrapping strategy to improve the anti-noisy label's ability. The results show that Cnngeno performs better in terms of precision for calling genotype when compared with other existing methods. The Cnngeno is an open-source method, available at https://github.com/BRF123/Cnngeno .