Negative binomial count splitting for single-cell RNA sequencing data

TL;DR

This paper introduces negative binomial count splitting for single-cell RNA sequencing data, enabling independent dataset creation for model validation in the presence of overdispersion.

Contribution

It extends Poisson count splitting to negative binomial models using Dirichlet-multinomial sampling, improving validation of scRNA-seq models with overdispersed data.

Findings

Outperforms Poisson count splitting in simulations

Successfully validated kidney cell clusters from human fetal atlas

Provides a flexible method for independent dataset generation

Abstract

The analysis of single-cell RNA sequencing (scRNA-seq) data often involves fitting a latent variable model to learn a low-dimensional representation for the cells. Validating such a model poses a major challenge. If we could sequence the same set of cells twice, we could use one dataset to fit a latent variable model and the other to validate it. In reality, we cannot sequence the same set of cells twice. Poisson count splitting was recently proposed as a way to work backwards from a single observed Poisson data matrix to obtain independent Poisson training and test matrices that could have arisen from two independent sequencing experiments conducted on the same set of cells. However, the Poisson count splitting approach requires that the original data are exactly Poisson distributed: in the presence of any overdispersion, the resulting training and test datasets are not independent. In this paper, we introduce negative binomial count splitting, which extends Poisson count splitting to the more flexible negative binomial setting. Given an $n \times p$ dataset from a negative binomial distribution, we use Dirichlet-multinomial sampling to create two or more independent $n \times p$ negative binomial datasets. We show that this procedure outperforms Poisson count splitting in simulation, and apply it to validate clusters of kidney cells from a human fetal cell atlas.