Non-parametric modelling of temporal and spatial counts data from RNA-seq experiments

Nuha Bintayyash, Sokratia Georgaka, S. T. John, Sumon Ahmed, Alexis Boukouvalas, James Hensman, Magnus Rattray

Abstract: The negative binomial distribution has been shown to be a good model for counts data from both bulk and single-cell RNA-sequencing (RNA-seq). Gaussian process (GP) regression provides a useful non-parametric approach for modelling temporal or spatial changes in gene expression. However, currently available GP regression methods that implement negative binomial likelihood models do not scale to the increasingly large datasets being produced by single-cell and spatial transcriptomics.