Biography:  Dr. Wang (Chinese: 王涛) is Tenure Track Associate Professor in the Department of Bioinformatics and Biostatistics and Principal Investigator in the SJTU-Yale Joint Center for Biostatistics and Data Science at Shanghai Jiao Tong University. He achieved his PhD degree in statistics at Hong Kong Baptist University, and was a Postdoctoral Associate in the Department of Biostatistics at Yale School of Public Health. Current areas of investigation include statistics for high-dimensional data, statistical machine learning, and biostatistics. He is an ISI elected member and an Assistant Professor Adjunct of Biostatistics at Yale School of Public Health.

Title: A Zero-Inflated Probabilistic PCA Model for Extracting Microbial Compositions

Abstract: High throughput sequencing data collected to study the microbiome provide information in the form of relative abundances and should be treated as compositions. Although many approaches including scaling and rarefaction have been proposed for converting raw count data into microbial compositions, most of these methods simply return zero values for zero counts. However, zeros can distort downstream analyses, and they can also pose problems for composition-aware methods. This problem is exacerbated with microbiome abundance data because they are sparse with excessive zeros. In addition to data sparsity, microbial composition estimation depends on other data characteristics such as high dimensionality, over-dispersion, and complex co-occurrence relationships. To address these challenges, we introduce a zero-inflated probabilistic PCA (ZIPPCA) model that accounts for the compositional nature of microbiome data, and propose an empirical Bayes approach to estimate microbial compositions. An efficient iterative algorithm, called classification variational approximation, is developed for carrying out maximum likelihood estimation. Moreover, we study the consistency and asymptotic normality of variational approximation estimator from the perspective of profile M-estimation. Extensive simulations and an application to a data set from the Human Microbiome Project are presented to compare the performance of the proposed method with that of the existing methods. The method is implemented in R and available at https://github.com/YanyZeng/ZIPPCAlnm.