Sparse Inverse Covariance Estimation for High-throughput microRNA Sequencing Data in the Poisson Log-Normal Graphical Model

TL;DR

This paper introduces a novel Poisson Log-Normal Graphical Model tailored for high-throughput microRNA sequencing data, enabling better network inference by accounting for overdispersion and dependencies, with demonstrated improved performance and biological relevance.

Contribution

The paper presents a new statistical model and an EM-based algorithm for network inference in count data, specifically addressing overdispersion in microRNA sequencing datasets.

Findings

Model outperforms existing methods in simulations

Identifies key miRNAs involved in breast cancer regulation

Provides a feasible approach for high-throughput count data analysis

Abstract

We introduce the Poisson Log-Normal Graphical Model for count data, and present a normality transformation for data arising from this distribution. The model and transformation are feasible for high-throughput microRNA (miRNA) sequencing data and directly account for known overdispersion relationships present in this data set. The model allows for network dependencies to be modeled, and we provide an algorithm which utilizes a one-step EM based result in order to allow for a provable increase in performance in determining the network structure. The model is shown to provide an increase in performance in simulation settings over a range of network structures. The model is applied to high-throughput miRNA sequencing data from patients with breast cancer from The Cancer Genome Atlas (TCGA). By selecting the most highly connected miRNA molecules in the fitted network we find that nearly all of them are known to be involved in the regulation of breast cancer.