A multi-task convolutional deep neural network for variant calling in single molecule sequencing
A multi-task convolutional deep neural network for variant calling in single molecule sequencing
复制标题
DOI：
10.1038/s41467-019-09025-z
复制
发表时间：
2019-03-01
影响因子：
16.6
通讯作者：
Schatz, Michael C.
中科院分区：
文献类型：
--
作者：
Luo, Ruibang;Sedlazeck, Fritz J.;Schatz, Michael C.
DNA序列变异的准确鉴定是基因组学中一项重要而又具有挑战性的任务。单分子测序尤其困难，其具有类似于5- 15%的每核苷酸错误率。为了满足这一需求，我们开发了Clairvoyante，这是一种多任务五层卷积神经网络模型，用于预测来自比对读数的变体类型（SNP或indel），接合性，替代等位基因和indel长度。对于充分表征的NA 12878人类样本，Clairvoyante分别使用Illumina、PacBio和Oxford Nanopore数据，在1 KP常见变异体上获得99.67、95.78、90.53%的F1评分，在全基因组分析中获得98.65、92.57、87.26%的F1评分。对第二个人类样本的训练表明，Clairvoyante是样本不可知的，并且在标准服务器上不到2小时就找到了变体。此外，我们提出了3，135个使用Illumina遗漏但由PacBio和Oxford Nanopore读数独立支持的变体。Clairvoyante是开源的（https：//github.com/aquaskyline/Clairvoyante），具有训练，利用和可视化模型的模块。
The accurate identification of DNA sequence variants is an important, but challenging task in genomics. It is particularly difficult for single molecule sequencing, which has a pernucleotide error rate of similar to 5-15%. Meeting this demand, we developed Clairvoyante, a multi-task five-layer convolutional neural network model for predicting variant type (SNP or indel), zygosity, alternative allele and indel length from aligned reads. For the well-characterized NA12878 human sample, Clairvoyante achieves 99.67, 95.78, 90.53% F1-score on 1KP common variants, and 98.65, 92.57, 87.26% F1-score for whole-genome analysis, using Illumina, PacBio, and Oxford Nanopore data, respectively. Training on a second human sample shows Clairvoyante is sample agnostic and finds variants in less than 2 h on a standard server. Furthermore, we present 3,135 variants that are missed using Illumina but supported independently by both PacBio and Oxford Nanopore reads. Clairvoyante is available open-source (https://github.com/aquaskyline/Clairvoyante), with modules to train, utilize and visualize the model.