Learning Sparse Log-Ratios for Compositional Data R package codacore version 0.0.4 CRAN Task View: CompositionalData (https://CRAN.R-project.org/view=CompositionalData) In the context of high-throughput genetic data, CoDaCoRe identifies a set of sparse biomarkers that are predictive of a response variable of interest (Gordon-Rodriguez et al., 2021) <doi:10.1093/bioinformatics/btab645>. More generally, CoDaCoRe can be applied to any regression problem where the independent variable is Compositional (CoDa), to derive a set of scale-invariant log-ratios (ILR or SLR) that are maximally associated to a dependent variable. Software Depends: R (>= 3.6.0) Imports: tensorflow (>= 2.1), keras (>= 2.3), pROC (>= 1.17), R6 (>= 2.5), gtools(>= 3.8) Suggests: zCompositions, testthat (>= 2.1.0), knitr, rmarkdown Elliott Gordon-Rodriguez <eg2912@columbia.edu> Comprehensive R Archive Network (CRAN) Elliott Gordon-Rodriguez [aut, cre], Thomas Quinn [aut] MIT + file LICENSE (https://CRAN.R-project.org/package=codacore/LICENSE) 2022-08-29 application/tgz https://CRAN.R-project.org/package=codacore doi:10.32614/CRAN.package.codacore