期刊
GENOME MEDICINE
卷 14, 期 1, 页码 -出版社
BMC
DOI: 10.1186/s13073-022-01120-z
关键词
Rare variant; Pathogenicity; Deep learning; Machine learning; Insertion; Deletion; Single nucleotide variant
资金
- National Human Genome Research Institute [1R03HG011075]
This study developed pathogenicity prediction models, MetaRNN and MetaRNN-indel, using context annotations and deep learning methods to improve the identification and prioritization of rare harmful genetic variants. These models outperform state-of-the-art competitors and achieve a more interpretable score distribution, making them suitable for integrated genotype-phenotype association analysis methods.
Multiple computational approaches have been developed to improve our understanding of genetic variants. However, their ability to identify rare pathogenic variants from rare benign ones is still lacking. Using context annotations and deep learning methods, we present pathogenicity prediction models, MetaRNN and MetaRNN-indel, to help identify and prioritize rare nonsynonymous single nucleotide variants (nsSNVs) and non-frameshift insertion/deletions (nflNDELs). We use independent test sets to demonstrate that these new models outperform state-of-the-art competitors and achieve a more interpretable score distribution. Importantly, prediction scores from both models are comparable, enabling easy adoption of integrated genotype-phenotype association analysis methods. All pre-computed nsSNV scores are available at http://www.liulab.science/MetaRNN . The stand-alone program is also available at https://github.com/Chang-Li2019/MetaRNN.
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