A Framework to Incorporate D-trace Loss into Compositional Data Analysis

Abstract

The development of high-throughput sequencing technologies for 16S rRNA gene profiling provides higher quality compositional data for microbe communities. Inferring the direct interaction network under a specific condition and understanding how the network structure changes between two different environmental or genetic conditions are two important topics in biological studies. However, the compositional nature and high dimensionality of the data are challenging in the context of network and differential network recovery. To address this problem in the present paper, we proposed a framework to incorporate the data transformations developed for compositional data analysis into D-trace loss for network and differential network estimation, respectively. The sparse matrix estimators are defined as the minimizer of the corresponding lasso penalized loss. This framework is characterized by its straightforward application based on the ADMM algorithm for numerical solution. Simulations show that the proposed method outperforms other state-of-the-art methods in network and differential network inference under different scenarios. Finally, as an illustration, our method is applied to a mouse skin microbiome data. Author summaryInferring the direct interactions among microbes and how these interactions change under different conditions are important to understand community-wide dynamics. The compositional nature and high dimensionality are two distinctive features of microbial data, which invalidate traditional correlation analysis and challenge interaction network estimation. In this study, we set up a framework that combines data transformation with D-trace loss to infer the direct interaction network and differential network from compositional data. Simulations and real data analysis show that our proposed methods lead to results with higher accuracy and stability.