Control-independent mosaic single nucleotide variant detection with DeepMosaic.
Control-independent mosaic single nucleotide variant detection with DeepMosaic.
复制标题
DOI：
10.1038/s41587-022-01559-w
复制
发表时间：
2023-06
影响因子：
46.9
通讯作者：
Gleeson, Joseph G.
中科院分区：
文献类型：
--
作者：
Yang, Xiaoxu;Xu, Xin;Breuss, Martin W.;Antaki, Danny;Ball, Laurel L. V.;Chung, Changuk;Shen, Jiawei;Li, Chen;George, Renee D.;Wang, Yifan;Bae, Taejeong;Cheng, Yuhe;Abyzov, Alexej M.;Wei, Liping;Alexandrov, Ludmil B.;Sebat, Jonathan L.;Gleeson, Joseph G.
镶嵌变体（MV）反映了胚胎发育和环境暴露期间的诱变过程，随着年龄的增长和潜在疾病（如癌症和自闭症）而积累。由于非克隆扩增MV的稀疏表示，非癌症MV的检测在计算上具有挑战性。在这里，我们介绍了DeepMosaic，它结合了一个基于图像的单核苷酸MV可视化模块和一个基于卷积神经网络的分类模块，用于独立于控制的MV检测。DeepMosaic在180，000个模拟或实验评估的MV上进行了训练，并在来自16个WGS和181个WES的619，740个模拟MV和530个独立生物测试MV上进行了基准测试。与现有的生物数据方法相比，DeepMosaic实现了更高的准确性，对非癌症WGS的灵敏度为0.78，特异性为0.83，阳性预测值为0.96，并且验证率比之前对非癌症WES数据的最佳实践方法提高了一倍（0.43 vs 0.18）。DeepMosaic代表了一种针对非癌症样本的准确MV分类器，可以作为现有方法的替代或补充。
Mosaic variants (MVs) reflect mutagenic processes during embryonic development and environmental exposure, accumulate with aging, and underlying diseases such as cancer and autism. The detection of noncancer MVs has been computationally challenging due to the sparse representation of non-clonally expanded MVs. Here we present DeepMosaic, combining an image-based visualization module for single nucleotide MVs, and a convolutional neural networks-based classification module for control-independent MV detection. DeepMosaic was trained on 180,000 simulated or experimentally-assessed MVs and was benchmarked on 619,740 simulated MVs, and 530 independent biologically tested MVs from 16 WGS, and 181 WES. DeepMosaic achieved higher accuracy compared with existing methods on biological data, with a sensitivity of 0.78, specificity of 0.83, and positive predictive value of 0.96 on noncancer WGS, as well as doubling the validation rate over prior best-practice methods on noncancer WES data (0.43 vs 0.18). DeepMosaic represents an accurate MV classifier for noncancer samples that can be implemented as an alternative or complement to existing methods.
登录
查看更多内容
影响因子：
82.9
作者：
Breuss, Martin W.;Antaki, Danny;Gleeson, Joseph G.
通讯作者：
Gleeson, Joseph G.
影响因子：
46.9
作者：
Dou, Yanmei;Kwon, Minseok;Park, Peter J.
通讯作者：
Park, Peter J.
影响因子：
46.9
作者：
Poplin, Ryan;Chang, Pi-Chuan;DePristo, Mark A.
通讯作者：
DePristo, Mark A.
通过多个器官的全基因组分析揭示健康个体中独特类型的合子后单核苷酸嵌合体
影响因子：
4.5
作者：
Huang, August Yue;Yang, Xiaoxu;Wei, Liping
通讯作者：
Wei, Liping
影响因子：
64.8
作者：
Karczewski, Konrad J;Francioli, Laurent C;MacArthur, Daniel G
通讯作者：
MacArthur, Daniel G