專題演講 主講人:賴恩語博士(中央研究院統計科學研究所)

題 目:Causal Inference and Genome-wide Multimediator Analyses
主講人:賴恩語博士 (中央研究院統計科學研究所)
時 間:114年3月28日(星期五)上午10:40-11:30
(上午10:20-10:40茶會於綜合一館428室舉行)
地 點:綜合一館427室
使用Google Meet線上直播,
演講開始前20分鐘可進入會議,請點選下列連結後按下「加入」即可https://meet.google.com/pie-jmyd-cra
摘要
Mediation analysis is performed to evaluate the effects of a hypothetical causal mechanism that marks the progression from an exposure, through mediators, to an outcome. In the age of high-throughput technologies, it has become routine to assess numerous potential mechanisms at the genome or proteome scales. Alongside this, the necessity to address issues related to multiple testing has also arisen. In a sparse scenario where only a few genes or proteins are causally involved, conventional methods for assessing mediation effects lose statistical power because the composite null distribution behind this experiment can not be attained. The power loss hence decreases the true mechanisms identified after multiple testing corrections. To fairly delineate a uniform distribution under the composite null, Huang (2019, AoAS) proposed the composite test to provide adjusted p-values for single-mediator analyses. Our contribution is to extend the method to multi-mediator analyses, which are commonly encountered in genomic studies and also flexible to various biological interests. Using the generalized Berk-Jones statistics with the composite test, we proposed a multivariate approach that favors dense and diverse mediation effects, a decorrelation approach that favors sparse and consistent effects, and a hybrid approach that captures the edges of both approaches. Our analysis suite has been implemented as an R package MACtest. The utility is demonstrated by analyzing the lung adenocarcinoma datasets from The Cancer Genome Atlas and Clinical Proteomic Tumor Analysis Consortium. We further investigate the genes and networks whose expression may be regulated by smoking-induced epigenetic aberrations.

