ulrb
Unsupervised Learning Based Definition of Microbial Rare Biosphere
Francisco Pascoal, Paula Branco, Luís Torgo, Catarina Magalhães
Last update: 17 November 2023
Software version identifier: 0.1.3
Copyright license: GNU General Public License
A tool to define rare biosphere. 'ulrb' solves the problem of the definition of rarity by replacing human decision with an unsupervised machine learning algorithm (partitioning around medoids, or k-medoids). This algorithm works for any type of microbiome data, provided there is an abundance score for each phylogenetic unit. For validation of this method to several kinds of molecular data and environments, please see Pascoal et al, 2023 (in preparation). Preliminary data suggest this method also works well for non-microbiome data, if there is a species abundance table.