Grade of Membership Model and Visualization for RNA-seq data using CountClust

Grade of membership or GoM models (also known as admixture models or Latent Dirichlet Allocation”) are a generalization of cluster models that allow each sample to have membership in multiple clusters. It is widely used to model ancestry of individuals in population genetics based on SNP/ microsatellite data and also in natural language processing for modeling documents [1, 3]. This R package implements tools to visualize the clusters obtained from fitting topic models using a Structure plot [2] and extract the top features/genes that distinguish the clusters. In presence of known technical or batch effects, the package also allows for correction of these confounding effects. CountClust version: 1.2.0 1 This document used the vignette from Bioconductor package DESeq2, cellTree as knitr template