期刊
BRIEFINGS IN BIOINFORMATICS
卷 22, 期 4, 页码 -出版社
OXFORD UNIV PRESS
DOI: 10.1093/bib/bbaa370
关键词
structural variant; variant calling; variant filtering; whole genome sequencing; deep learning; convolutional neural network
资金
- Natural Science Foundation of China [31701147 62072140]
- China Postdoctoral Science Foundation [2018 M631934, 2018 T110300]
- Heilongjiang Postdoctoral Financial Assistance [LBH-Z17070]
- Fundamental Research Funds for the Central Universities [HIT.NSRIF.2019055]
- National Key R&D Program of China [2017YFC0907500]
Short read whole genome sequencing is widely used in human genetic studies and clinical practices for detecting structural variants, but accurate detection is challenging. This study introduces a novel deep learning-based approach, DeepSVFilter, for filtering structural variants in short read whole genome sequencing data.
Short read whole genome sequencing has become widely used to detect structural variants in human genetic studies and clinical practices. However, accurate detection of structural variants is a challenging task. Especially existing structural variant detection approaches produce a large proportion of incorrect calls, so effective structural variant filtering approaches are urgently needed. In this study, we propose a novel deep learning-based approach, DeepSVFilter, for filtering structural variants in short read whole genome sequencing data. DeepSVFilter encodes structural variant signals in the read alignments as images and adopts the transfer learning with pre-trained convolutional neural networks as the classification models, which are trained on the well-characterized samples with known high confidence structural variants. We use two well-characterized samples to demonstrate DeepSVFilter's performance and its filtering effect coupled with commonly used structural variant detection approaches.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据