The Deep Generative Decoder: MAP estimation of representations improves modeling of single-cell RNA data

Learning low-dimensional representations of single-cell transcriptomics has become instrumental to its downstream analysis. The state of the art is currently represented by neural network models such as Variational Autoencoders (VAEs) which use a variational approximation of the likelihood for inference. We here present the Deep Generative Decoder (DGD), a simple generative model that computes model parameters and representations directly via maximum a posteriori (MAP) estimation. The DGD handles complex parametrized latent distributions naturally unlike VAEs which typically use overly simple fixed Gaussian distributions. We first show its general functionality and superiority in data generation on a commonly used benchmark set, Fashion-MNIST. Secondly, we apply the model to a single-cell dataset from peripheral blood mononuclear cells. Here the DGD learns low-dimensional, meaningful and well-structured latent representations with sub-clustering beyond the provided labels. The advantages of this approach are its simplicity and its capability to provide representations of much smaller dimensionality than a comparable VAE.