Single cell RNA-Seq data is challenging to analyse due to problems like dropout and cell type identification. We present a novel clustering
approach that applies mixture models to learn interpretable clusters from RNA-Seq data, and demonstrate how it can be applied to publicly
available scRNA-Seq data from the mouse brain. Having inferred groupings of the cells, we can then attempt to learn networks from the data. These approaches are widely applicable to single cell RNA-Seq datasets where there is a need to identify and characterise sub-populations of cells.