A machine learning approach to brain epigenetic analysis reveals kinases associated with Alzheimer's disease.
A machine learning approach to brain epigenetic analysis reveals kinases associated with Alzheimer's disease.
复制标题
DOI：
10.1038/s41467-021-24710-8
复制
发表时间：
2021-07-22
影响因子：
16.6
通讯作者：
Qin ZS
中科院分区：
文献类型：
--
作者：
Huang Y;Sun X;Jiang H;Yu S;Robins C;Armstrong MJ;Li R;Mei Z;Shi X;Gerasimov ES;De Jager PL;Bennett DA;Wingo AP;Jin P;Wingo TS;Qin ZS
阿尔茨海默病（AD）受遗传和环境因素的影响，因此，脑表观基因组的改变可能会提供洞察AD的发病机制。多个基于阵列的表观全基因组关联研究（EWAS）已经确定了AD中强大的脑甲基化变化;然而，基于阵列的测定仅检测基因组中约2%的所有CpG位点。在这里，我们开发了EWASplus，这是一种使用监督机器学习策略将EWAS覆盖范围扩展到整个基因组的计算方法。应用六种AD相关特征预测了数百个与AD相关的新的重要大脑CpGs，其中一些得到了进一步的实验验证。EWASplus在从独立队列和不同大脑区域收集的数据上也表现良好。在顶部EWASplus基因座附近发现的基因富含激酶和与已知AD基因物理相互作用的证据。在这项工作中，我们表明，EWASplus涉及额外的表观遗传位点的AD，没有发现使用基于阵列的AD EWASs。基于阵列的表观基因组关联研究仅测试基因组中约2%的CpG位点。在这里，作者描述了EWASplus，一种监督机器学习策略，将EWAS覆盖范围扩展到整个基因组，并使用它来识别与阿尔茨海默病相关的新型大脑CpG。
Alzheimer’s disease (AD) is influenced by both genetic and environmental factors; thus, brain epigenomic alterations may provide insights into AD pathogenesis. Multiple array-based Epigenome-Wide Association Studies (EWASs) have identified robust brain methylation changes in AD; however, array-based assays only test about 2% of all CpG sites in the genome. Here, we develop EWASplus, a computational method that uses a supervised machine learning strategy to extend EWAS coverage to the entire genome. Application to six AD-related traits predicts hundreds of new significant brain CpGs associated with AD, some of which are further validated experimentally. EWASplus also performs well on data collected from independent cohorts and different brain regions. Genes found near top EWASplus loci are enriched for kinases and for genes with evidence for physical interactions with known AD genes. In this work, we show that EWASplus implicates additional epigenetic loci for AD that are not found using array-based AD EWASs. Array-based epigenome-wide association studies only test about 2% of the CpG sites in the genome. Here, the authors describe EWASplus, a supervised machine learning strategy that extends EWAS coverage to the entire genome, and use it to identify novel brain CpGs associated with Alzheimer’s disease.
登录
查看更多内容
DOI：
10.1126/science.1260793
发表时间：
2015-02-06
期刊：
Science (New York, N.Y.)
影响因子：
--
作者：
Battle A;Khan Z;Wang SH;Mitrano A;Ford MJ;Pritchard JK;Gilad Y
通讯作者：
Gilad Y
DOI：
10.3233/jad-179939
发表时间：
2018
期刊：
Journal of Alzheimer's disease : JAD
影响因子：
--
作者：
Bennett DA;Buchman AS;Boyle PA;Barnes LL;Wilson RS;Schneider JA
通讯作者：
Schneider JA
影响因子：
12.3
作者：
Chen L;Jin P;Qin ZS
通讯作者：
Qin ZS
影响因子：
9.8
作者：
De Jager, Philip L.;Ma, Yiyi;Bennett, David A.
通讯作者：
Bennett, David A.
影响因子：
25
作者：
De Jager, Philip L.;Srivastava, Gyan;Lunnon, Katie;Burgess, Jeremy;Schalkwyk, Leonard C.;Yu, Lei;Eaton, Matthew L.;Keenan, Brendan T.;Ernst, Jason;McCabe, Cristin;Tang, Anna;Raj, Towfique;Replogle, Joseph;Brodeur, Wendy;Gabriel, Stacey;Chai, High S.;Younkin, Curtis;Younkin, Steven G.;Zou, Fanggeng;Szyf, Moshe;Epstein, Charles B.;Schneider, Julie A.;Bernstein, Bradley E.;Meissner, Alex;Ertekin-Taner, Nilufer;Chibnik, Lori B.;Kellis, Manolis;Mill, Jonathan;Bennett, David A.
通讯作者：
Bennett, David A.