Package: MeLSI Type: Package Title: Metric Learning for Statistical Inference in Microbiome Analysis Version: 1.1.7 Authors@R: c(person("Nathan", "Bresette", email = "nathanbresette04@gmail.com", role = c("aut", "cre"), comment = c(ORCID = "0009-0003-1554-6006")), person("Aaron C.", "Ericsson", role = "aut", comment = c(ORCID = "0000-0002-3053-7269")), person("Carter", "Woods", role = "aut", comment = c(ORCID = "0009-0007-5345-2712")), person("Ai-Ling", "Lin", role = c("aut", "fnd"), comment = c(ORCID = "0000-0002-5197-2219"))) Description: MeLSI (Metric Learning for Statistical Inference) is a novel machine learning method for microbiome data analysis that learns optimal distance metrics to improve statistical power in detecting group differences. Unlike traditional distance metrics (Bray-Curtis, Euclidean, Jaccard), MeLSI adapts to the specific characteristics of your dataset to maximize separation between groups. The method uses an ensemble of weak learners to identify which microbial features drive group differences, providing both improved statistical power and biological interpretability through feature importance weights. License: MIT + file LICENSE Encoding: UTF-8 RoxygenNote: 7.3.3 Depends: R (>= 4.5.0) URL: https://github.com/NathanBresette/MeLSI BugReports: https://github.com/NathanBresette/MeLSI/issues Imports: ggplot2, stats, utils, Rcpp LinkingTo: Rcpp Suggests: testthat, knitr, rmarkdown, BiocManager, BiocStyle, BiocParallel, Matrix, microbiome, phyloseq, vegan VignetteBuilder: knitr biocViews: Software, StatisticalMethod, Microbiome Repository: https://bioc.r-universe.dev Date/Publication: 2026-06-17 21:23:49 UTC RemoteUrl: https://github.com/bioc/MeLSI RemoteRef: HEAD RemoteSha: 19902ee27eb55b11d471d7afb62c7e53eccba723 NeedsCompilation: yes Packaged: 2026-07-18 08:47:04 UTC; root Author: Nathan Bresette [aut, cre] (ORCID: ), Aaron C. Ericsson [aut] (ORCID: ), Carter Woods [aut] (ORCID: ), Ai-Ling Lin [aut, fnd] (ORCID: ) Maintainer: Nathan Bresette