Abstract:
Studies on the human microbiome (人体微生物组) have revealed that differences in microbial communities (细菌群落) are associated with many human disorders, such as inflammatory bowel disease (炎症性肠病), type II diabetes (二型糖尿病), cancers (癌症), and even Alzheimer’s disease (阿尔茨海默氏病). The microbiome is a particularly attractive target for establishing new biomarkers for disease diagnosis and prognosis, and for developing low-cost, low-risk interventions. Microbiome data are compositional, i.e., the total number of sequencing reads per sample is an experimental artifact and only the relative abundance of microbial species can be measured. This unique feature calls for analyses that are based on log-ratio transformation of the raw count data. Existing methods often failed to handle the extensive (50-90%) zero counts adequately as well as accommodating other complexities in microbiome data, including high-dimensionality, over-dispersion, small sample size, and various types of covariates of interest and confounding factors. In this talk, we present a new logistic-regression-based method that takes into account all of these features of microbiome data for robust testing of differential abundance (i.e., detecting taxa whose absolute abundance is associated with the covariate of interest). Our simulation studies indicate that our method is the only one that universally controls the false-discovery rate while at the same time maintaining high power. I will illustrate our method by an application to a throat microbiome dataset, in which we discovered that several throat microbial species were affected by smoking.
Biography:
胡懿娟，美国埃默里（Emory）公共卫生学院（School of Public Health, #4 by U.S.News ranking）生物统计与生物信息系（Department of Biostatistics and Bioinformatics）副教授。本科毕业于304am永利集团概率统计系（2001-2005），留学美国北卡罗莱大学教堂山分校获生物统计学博士（2011）。现在主要研究领域为微生物组统计学，开发统计方法对（肠道，口腔）微生物组数据进行关联分析或者因果分析，同时应用到实际研究数据中揭示复杂性状或疾病（比如炎症性肠病，二型糖尿病，癌症）的微生物机制，从而协助开发基于微生物的预测或疗法。代表工作发表于 Journal of American Statistical Association (JASA) 、Proceedings of the National Academy of Sciences (PNAS) 、Microbiome、American Journal of Human Genetics (AJHG) 、等期刊。
Tencent Meeting：https://meeting.tencent.com/dm/vm4pPRaqhfMd
Meeting ID：744 281 818
