National Center for PTSD, VA Boston Healthcare System, Boston, MA 02130, USA.
Department of Biostatistics, Boston University School of Public Health, Boston, MA 02118, USA.
Epigenomics. 2019 Jul;11(9):1089-1105. doi: 10.2217/epi-2018-0204. Epub 2019 Jun 26.
We compared the performance of multiple testing corrections for candidate gene methylation studies, namely Sidak (accurate Bonferroni), false-discovery rate and three adjustments that incorporate the correlation between CpGs: extreme tail theory (ETT), Gao (GEA), and Li and Ji methods. The experiment-wide type 1 error rate was examined in simulations based on Illumina EPIC and 450K data. For high-correlation genes, Sidak and false-discovery rate corrections were conservative while the Li and Ji method was liberal. The GEA method tended to be conservative unless a threshold parameter was adjusted. The ETT yielded an appropriate type 1 error rate. For genes with substantial correlation across measured CpGs, GEA and ETT can appropriately correct for multiple testing in candidate gene methylation studies.
我们比较了候选基因甲基化研究中多重检验校正的性能,即 Sidak(准确的 Bonferroni)、错误发现率以及三种考虑 CpG 之间相关性的调整方法:极端尾部理论(ETT)、Gao(GEA)和 Li 和 Ji 方法。我们基于 Illumina EPIC 和 450K 数据进行了模拟,以检查实验范围内的第一类错误率。对于高相关基因,Sidak 和错误发现率校正方法较为保守,而 Li 和 Ji 方法则较为宽松。除非调整阈值参数,否则 GEA 方法往往较为保守。ETT 产生了适当的第一类错误率。对于在测量的 CpG 之间具有显著相关性的基因,GEA 和 ETT 可以适当校正候选基因甲基化研究中的多重检验。