A deep learning approach for filtering structural variants in short read sequencing data
A deep learning approach for filtering structural variants in short read sequencing data
复制标题
一种过滤短读长测序数据中结构变异的深度学习方法
DOI：
10.1093/bib/bbaa370
复制
发表时间：
2021-07-01
影响因子：
9.5
通讯作者：
Wang, Yadong
中科院分区：
文献类型：
--
作者：
Liu, Yongzhuang;Huang, Yalin;Wang, Yadong
短读全基因组测序已被广泛用于检测人类遗传研究和临床实践中的结构变异。然而，准确检测结构变异是一项具有挑战性的任务。特别是现有的结构变异检测方法产生了很大比例的错误调用，因此迫切需要有效的结构变异过滤方法。在这项研究中，我们提出了一种新的基于深度学习的方法DeepSVFilter，用于过滤短读全基因组测序数据中的结构变体。DeepSVFilter将读段比对中的结构变异信号编码为图像，并采用预训练卷积神经网络的迁移学习作为分类模型，该模型在具有已知高置信度结构变异的良好表征的样本上进行训练。我们使用两个充分表征的样本来展示DeepSVFilter的性能及其过滤效果，以及常用的结构变体检测方法。软件DeepSVFilter使用Python实现，可从网站https://github.com/yongzhuang/DeepSVFilter免费获得。
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. The software DeepSVFilter is implemented using Python and freely available from the website at https://github.com/yongzhuang/DeepSVFilter.