Softwares

  • R package maskmeans : This package is devoted to perform an aggregation / splitting multi-view K-means algorithm, starting with an initial clustering partition or matrix of posterior probabilities. The goal is to refine/improve the clustering obtained on the first, primary view by using additional data views; in addition, views which contain only noise or partially concordant information are down-weighted by the algorithm.
  • The Bioconductor package coseq:  This package is devoted to the co-expression analysis of sequencing data. It contains the Poisson mixture models developed in HTSCluster (see below), the strategy based on Gaussian mixture models on transformed profiles (see Rau and Maugis-Rabusseau, 2016 for more details) and the use of the K-means algorithm for RNA-seq profiles after transformation via the centered log ratio (CLR) or log centered log ratio (logCLR) transformation (see Godichon-Baggioni et al, 2017).

To install coseq, start R and enter

source("https://bioconductor.org/biocLite.R")
biocLite("coseq")

A quick-start guide is available here

  • R package HTSCluster: This package implements two parameterizations of a Poisson mixture model to cluster observations (e.g., genes) in high throughput sequencing data. Parameter estimation is performed using either the EM or CEM algorithm, and the BIC or ICL criteria are used for model selection (i.e., to choose the number of clusters).
  • R package HTSDiff: This package implements a Poisson mixture model to identify differentially expressed genes from RNA-seq data.
  • Variable selection algorithm in model-based clustering corresponding to
    • the SR modeling presented in Maugis et al. (2009, Biometrics) : SelvarClust
    • the SRUW modeling presented in Maugis et al.(2009, CSDA): SelvarClustIndep
    • the SR modeling with missing value presented in Maugis et al.(2012, Journal de la SFdS): SelvarClustMV
  • The R-package SelvarMix for variable selection in model-based clustering and discriminant analysis with a regularization approach
  • The Capushe software for model selection through penalized criteria devoted to penalty calibration based on the slope heuristics.