KODAMA1

KODAMA

Introduction

# KODAMA An unsupervised and semi-supervised learning algorithm to perform feature extraction from noisy and high-dimensional data

News

KODAMA facilitates identification of patterns representing underlying groups on all samples in a data set. This is an improved version of KODAMA algorithm for spatially-aware dimensionality reduction. A landmarks procedure has been implemented to adapt the algorithm to the analysis of data set with more than 10,000 entries.

The KODAMA package has been integrated with t-SNE and UMAP to convert the KODAMA's dissimilarity matrix in a low dimensional space.

Zinga, M. M., Abdel-Shafy, E., Melak, T., Vignoli, A., Piazza, S., Zerbini, L. F., ... & Cacciatore, S. (2022). KODAMA exploratory analysis in metabolic phenotyping. Frontiers in Molecular Biosciences, 9.
Cacciatore, S., Tenori, L., Luchinat, C., Bennett, P. R., & MacIntyre, D. A. (2017). KODAMA: an R package for knowledge discovery and data mining. Bioinformatics, 33(4), 621-623.
Cacciatore, S., Luchinat, C., & Tenori, L. (2014). Knowledge discovery by accuracy maximization. Proceedings of the National Academy of Sciences, 111(14), 5117-5122.

Installation

The KODAMA is available on CRAN.


library(devtools)
install_github("tkcaccia/KODAMA")

Applications

Metabolomic data

Explore Metabolomic data

Single cell RNA seq data

Explore Single cell RNA seq data

Spatial Transcriptomic data

Explore Spatial Transcriptomic data