Xu Lizhen, Paterson Andrew D, Xu Wei
Program in Genetics and Genome Biology, The Hospital for Sick Children, Toronto, ON, M5G 0A4, Canada.
Dalla Lana School of Public Health, University of Toronto, ON, M5T 3M7, Canada.
Genet Epidemiol. 2017 Apr;41(3):221-232. doi: 10.1002/gepi.22031. Epub 2017 Jan 22.
Motivated by the multivariate nature of microbiome data with hierarchical taxonomic clusters, counts that are often skewed and zero inflated, and repeated measures, we propose a Bayesian latent variable methodology to jointly model multiple operational taxonomic units within a single taxonomic cluster. This novel method can incorporate both negative binomial and zero-inflated negative binomial responses, and can account for serial and familial correlations. We develop a Markov chain Monte Carlo algorithm that is built on a data augmentation scheme using Pólya-Gamma random variables. Hierarchical centering and parameter expansion techniques are also used to improve the convergence of the Markov chain. We evaluate the performance of our proposed method through extensive simulations. We also apply our method to a human microbiome study.
受微生物组数据的多变量性质（具有分层分类簇、通常呈偏态且零膨胀的计数以及重复测量）的驱动，我们提出了一种贝叶斯潜变量方法，用于在单个分类簇内联合建模多个操作分类单元。这种新方法可以纳入负二项式和零膨胀负二项式响应，并可以考虑序列和家族相关性。我们开发了一种基于使用Pólya - Gamma随机变量的数据增强方案的马尔可夫链蒙特卡罗算法。还使用了分层中心化和参数扩展技术来提高马尔可夫链的收敛性。我们通过广泛的模拟评估了我们提出的方法的性能。我们还将我们的方法应用于一项人类微生物组研究。
