KODAMA: Knowledge Discovery by Accuracy Maximization

A self-guided, weakly supervised learning algorithm for feature extraction from noisy and high-dimensional data. It facilitates the identification of patterns that reflect underlying group structures across all samples in a dataset. The method incorporates a novel strategy to integrate spatial information, improving the interpretability of results in spatially resolved data.

Version: 3.0
Depends: R (≥ 2.10.0), stats, Rtsne, umap
Imports: Rcpp (≥ 0.12.4), Rnanoflann, methods, Matrix
LinkingTo: Rcpp, RcppArmadillo, Rnanoflann, Matrix
Suggests: rgl, knitr, rmarkdown
Published: 2025-06-03
DOI: 10.32614/CRAN.package.KODAMA
Author: Stefano Cacciatore ORCID iD [aut, trl, cre], Leonardo Tenori ORCID iD [aut]
Maintainer: Stefano Cacciatore <tkcaccia at gmail.com>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: yes
Materials: README
CRAN checks: KODAMA results

Documentation:

Reference manual: KODAMA.pdf
Vignettes: Knowledge Discovery by Accuracy Maximization (source)

Downloads:

Package source: KODAMA_3.0.tar.gz
Windows binaries: r-devel: KODAMA_3.0.zip, r-release: KODAMA_3.0.zip, r-oldrel: KODAMA_3.0.zip
macOS binaries: r-release (arm64): KODAMA_3.0.tgz, r-oldrel (arm64): KODAMA_3.0.tgz, r-release (x86_64): KODAMA_3.0.tgz, r-oldrel (x86_64): KODAMA_3.0.tgz
Old sources: KODAMA archive

Reverse dependencies:

Reverse depends: MetChem

Linking:

Please use the canonical form https://CRAN.R-project.org/package=KODAMA to link to this page.