Structure learning for zero-inflated counts, with an application to single-cell RNA sequencing data

TL;DR

This paper introduces a new framework for inferring graph structures from single-cell RNA sequencing data, effectively handling high-dimensional, zero-inflated count data with high variance.

Contribution

The paper proposes a novel structure learning method based on zero-inflated negative binomial models tailored for single-cell RNA-seq data, addressing challenges of zeros and over-dispersion.

Findings

Successfully retrieves graph structures in simulations

Effective on real single-cell RNA-seq data

Handles high-dimensional, zero-inflated counts

Abstract

The problem of estimating the structure of a graph from observed data is of growing interest in the context of high-throughput genomic data, and single-cell RNA sequencing in particular. These, however, are challenging applications, since the data consist of high-dimensional counts with high variance and over-abundance of zeros. Here, we present a general framework for learning the structure of a graph from single-cell RNA-seq data, based on the zero-inflated negative binomial distribution. We demonstrate with simulations that our approach is able to retrieve the structure of a graph in a variety of settings and we show the utility of the approach on real data.