DeepPerVar: a multi-modal deep learning framework for functional interpretation of genetic variants in personal genome.
DeepPerVar: a multi-modal deep learning framework for functional interpretation of genetic variants in personal genome.
复制标题
DeepPerVar：一个多模式深度学习框架，用于个人基因组中遗传变异的功能解释。
DOI：
10.1093/bioinformatics/btac696
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Chen,Li
中科院分区：
文献类型：
--
作者：
Wang,Ye;Chen,Li
理解遗传变异的功能后果，特别是非编码的，是重要的，但特别具有挑战性。全基因组关联研究（GWAS）或数量性状基因座分析可能会受到有限的统计能力和连锁不平衡，因此不太适合查明因果变异。此外，大多数现有的机器学习方法，利用功能注释来解释和优先考虑推定的因果变异，不能适应人群研究中的个人遗传变异和性状的异质性，针对特定疾病。我们提出了一个多模态深度学习框架，通过考虑个人遗传变异和特征来预测全基因组定量表观遗传信号。所提出的方法可以通过量化预测的表观遗传信号的等位基因差异来进一步评估非编码变体在个体水平上的功能后果。通过将该方法应用于研究阿尔茨海默病（AD）的ROSMAP队列，我们证明了所提出的方法可以准确地预测定量全基因组表观遗传信号，并在AD致病基因的关键基因组区域中，学习报告调节AD致病基因的基因表达的典型基序，改善分区遗传力分析，并优先考虑GWAS风险位点中的推定致病变体。最后，我们将建议的深度学习模型作为独立的Python工具包和Web服务器发布。可用性和实施https：github.com/lichen-lab/DeepPerVar.Supplementary信息补充数据可在Bioinformaticsonline获得。
MotivationUnderstanding the functional consequence of genetic variants, especially the non-coding ones, is important but particularly challenging. Genome-wide association studies (GWAS) or quantitative trait locus analyses may be subject to limited statistical power and linkage disequilibrium, and thus are less optimal to pinpoint the causal variants. Moreover, most existing machine-learning approaches, which exploit the functional annotations to interpret and prioritize putative causal variants, cannot accommodate the heterogeneity of personal genetic variations and traits in a population study, targeting a specific disease.ResultsBy leveraging paired whole-genome sequencing data and epigenetic functional assays in a population study, we propose a multi-modal deep learning framework to predict genome-wide quantitative epigenetic signals by considering both personal genetic variations and traits. The proposed approach can further evaluate the functional consequence of non-coding variants on an individual level by quantifying the allelic difference of predicted epigenetic signals. By applying the approach to the ROSMAP cohort studying Alzheimer’s disease (AD), we demonstrate that the proposed approach can accurately predict quantitative genome-wide epigenetic signals and in key genomic regions of AD causal genes, learn canonical motifs reported to regulate gene expression of AD causal genes, improve the partitioning heritability analysis and prioritize putative causal variants in a GWAS risk locus. Finally, we release the proposed deep learning model as a stand-alone Python toolkit and a web server.Availability and implementationhttps://github.com/lichen-lab/DeepPerVar.Supplementary informationSupplementary data are available atBioinformaticsonline.