Simulating ComBat: how batch correction can lead to the systematic introduction of false positive results in DNA methylation microarray studies
Simulating ComBat: how batch correction can lead to the systematic introduction of false positive results in DNA methylation microarray studies
复制标题
DOI：
10.1186/s12859-020-03559-6
复制
发表时间：
2020-06-30
影响因子：
3
通讯作者：
Friedel, Eva
中科院分区：
文献类型：
--
作者：
Zindler, Tristan;Frieling, Helge;Friedel, Eva
背景在分析DNA甲基化（DNAm）微阵列数据时，系统性技术效应（也称为批次效应）是一个相当大的挑战，因为当与感兴趣的变量混淆时，它们可能导致错误的结果。正如以前的研究结果所示，纠正这些批次效应的方法容易出错。结果在这里，我们演示了如何使用R函数ComBat来校正模拟的Infinium HumanMethylation450 BeadChip（450 K）和Infinium MethylationEPIC BeadChip Kit（EPIC）DNAm数据，在某些条件下可能会导致大量的假阳性结果。我们进一步提供了一个详细的评估的后果，高度相关的问题ofp值膨胀与随后的假阳性结果后，经常使用的ComBat方法的应用。使用ComBat校正随机生成的样本中的批次效应产生了令人震惊的错误发现率（FDR）和Bonferroni校正（BF）假阳性结果，这些结果在探针测量期间感兴趣变量的结果与样本的技术位置之间的关系方面不平衡以及平衡的样本分布。系统模拟样本量和批次因素数量（例如芯片数量），以评估假阳性结果的概率。使用n = 48至t = 768个随机生成的样本模拟样本量的影响。增加校正因子的数量导致假阳性信号的数量呈指数增加。增加样本数量可以减少，但不能完全防止这种影响。结论使用所描述的方法，我们证明，使用ComBat的DNAm数据的批量校正可能会导致假阳性结果在某些条件下和样本分布。因此，我们的研究结果与以前的出版物相反，考虑使用ComBat时平衡的样本分布是没有问题的。我们并不声称报告所有技术条件和发生问题的可能解决方案的完整性，因为我们是从临床医生的角度而不是从计算机科学家的角度来解决问题的。通过我们的模拟数据方法，我们为读者提供了一种简单的方法来评估DNAm微阵列数据分析管道中假阳性结果的概率。
Background Systematic technical effects-also called batch effects-are a considerable challenge when analyzing DNA methylation (DNAm) microarray data, because they can lead to false results when confounded with the variable of interest. Methods to correct these batch effects are error-prone, as previous findings have shown. Results Here, we demonstrate how using the R function ComBat to correct simulated Infinium HumanMethylation450 BeadChip (450 K) and Infinium MethylationEPIC BeadChip Kit (EPIC) DNAm data can lead to a large number of false positive results under certain conditions. We further provide a detailed assessment of the consequences for the highly relevant problem ofp-value inflation with subsequent false positive findings after application of the frequently used ComBat method. Using ComBat to correct for batch effects in randomly generated samples produced alarming numbers of false discovery rate (FDR) and Bonferroni-corrected (BF) false positive results in unbalanced as well as in balanced sample distributions in terms of the relation between the outcome of interest variable and the technical position of the sample during the probe measurement. Both sample size and number of batch factors (e.g. number ofchips) were systematically simulated to assess the probability of false positive findings. The effect of sample size was simulated usingn = 48 up ton = 768 randomly generated samples. Increasing the number of corrected factors led to an exponential increase in the number of false positive signals. Increasing the number of samples reduced, but did not completely prevent, this effect. Conclusions Using the approach described, we demonstrate, that using ComBat for batch correction in DNAm data can lead to false positive results under certain conditions and sample distributions. Our results are thus contrary to previous publications, considering a balanced sample distribution as unproblematic when using ComBat. We do not claim completeness in terms of reporting all technical conditions and possible solutions of the occurring problems as we approach the problem from a clinician's perspective and not from that of a computer scientist. With our approach of simulating data, we provide readers with a simple method to assess the probability of false positive findings in DNAm microarray data analysis pipelines.