報告題目：Mixed model enrichment analysis of gene expression data
報 告 人：Duo Jiang 教授 美國俄勒岡州立大學
報告時間：2019年7月10日上午10:20-11:00
報告地點：數學樓一樓第一報告廳
報告摘要:
Competitive gene-set analysis, also called enrichment analysis, is a widely used tool for interpreting high-throughput biological data such as gene expression data. It aims at testing a known category (e.g. a pathway) of genes for enriched differential expression (DE) signals compared to genes not in the category. Most conventional enrichment testing methods ignore the widespread correlations among genes, which has been shown to result in excessive false positives. We evaluate, both methodologically and empirically, previous methods to account for correlations, and show that they fail to accommodate the DE heterogeneity across genes and can result in severely mis-calibrated type I error and/or power loss. We propose a new framework, MEACA, for gene-set testing based on a mixed effects quasi-likelihood model. Our method flexibly incorporates the unknown distribution of DE effects, and effectively adjusts for completely unknown, unstructured correlations among genes. Compared to existing methods such as GSEA and CAMERA, MEACA enjoys robust and substantially improved control over type I error and maintains good power in a variety of correlation structure and differential expression settings. We also present two real data analyses to illustrate the advantage of our approach.
報告人簡介：
Duo Jiang是美國俄勒岡州立大學的助理教授。 她于2014年獲得了芝加哥大學的統計學博士學位，在此之前她獲得了清華大學的學士學位。她的研究重點是開發遺傳學和基因組學數據的統計方法。最近的一些項目涉及微生物組數據分析，基因表達數據的富集分析以及多組學數據整合。
