JoshuaTian/EpiCluster: Clustering of (epigenetic) DNA methylation data using a variational Bayes NMF algorithm

EpiCluster is a dimensional reduction and clustering algorithm specifically designed for large DNA methylation datasets, e.g. Epigenome-Wide Association Studies (EWAS). The method is based on a variational Bayes non-negative matrix factorization (NMF) method, which preserves the bounded beta-valued nature of DNA methylation data. This NMF method is used for dimensional reduction and can be used in conjunction with the RPBMM algorithm. Users can used the algorithm for (i) dimensional reduction and inference of components of variation, (ii) for unsupervised clustering and for (iii) feature selection.

install.packages("remotes")
remotes::install_github("JoshuaTian/EpiCluster")