MCMC.OTU - Bayesian Analysis of Multivariate Counts Data in DNA
Metabarcoding and Ecology
Poisson-lognormal generalized linear mixed model analysis
of multivariate counts data using MCMC, aiming to infer the
changes in relative proportions of individual variables. The
package was originally designed for sequence-based analysis of
microbial communities ("metabarcoding", variables = operational
taxonomic units, OTUs), but can be used for other types of
multivariate counts, such as in ecological applications
(variables = species). The results are summarized and plotted
using 'ggplot2' functions. Includes functions to remove sample
and variable outliers and reformat counts into normalized
log-transformed values for correlation and principal
component/coordinate analysis. Walkthrough and examples:
http://www.bio.utexas.edu/research/matz_lab/matzlab/Methods_files/walkthroughExample_mcmcOTU_R.txt.
