CoMiCoN

CoMiCoN is an R package for microbial covariation and network analysis. It uses a mixture margin copula model to model a pair of microbial relative abundances. The copula dependence parameter, \(\theta\), captures the covariation for the pair of microbes and can be used to build covariation networks. The package implements a two-stage maximum likelihood estimation (tsMLE) procedure and a two-stage likelihood ratio test (tsLRT) for the CoMiCoN model. For information can be found here.

zinLDA

Zero-inflated latent Dirichlet allocation (zinLDA) is an unsupervised, hierarchical, generative probabilistic model that facilitates dimensionality reduction and detection of sparse latent clusters. This package provides implementation of a Markov chain Monte Carlo (MCMC) sampling procedure for the zinLDA model. Additionally, it provides a method for simulating sparse count data from an underlying zinLDA model. While the original paper developed this model for applications to microbiome data and microbial subcommunity detection, it is designed to be portable to numerous types of discrete count data.