This package implements algorithms for structure learning of graphical models for count data.

The function PCzinb implements three algorithms to estimate the structure of a graph from the input data.

The function simdata can be used to simulate data.

The preferred way to install the package is

if (!require("BiocManager", quietly = TRUE))
    install.packages("BiocManager")
BiocManager::install("drisso/learn2count")

Please, see the vignette for detailed examples of the package usage.

The analyses and figures of the Nguyen et al. (2023) paper were done with package version 0.1.3, which can be found here. Please use this version to reproduce the results of the paper.

The analyses and figures of the Nguyen et al. (2022) paper were done with package version 0.3.0, which can be found here. Please use this version to reproduce the results of the paper.

For virtually all other uses, we recommend using the latest stable version of the package (corresponding to the master branch).

Nguyen, Van den Berge, Chiogna, Risso (2023). Structure learning for zero- inflated counts, with an application to single-cell RNA sequencing data. Annals of Applied Statistics.

Nguyen, Chiogna, Risso, Banzato (2024). Guided structure learning of DAGs for count data. Statistical Modelling. In print. Preprint.