Current clustering priors for deep latent variable models (DLVMs) require
defining the number of clusters a-priori and are susceptible to poor
initializations. Addressing these deficiencies could greatly benefit deep
learning-based scRNA-seq analysis by performing integration and clustering
simultaneously. We adapt the VampPrior (Tomczak & Welling, 2018) into a
Dirichlet process Gaussian mixture model, resulting in the VampPrior Mixture
Model (VMM), a novel prior for DLVMs. We propose an inference procedure that
alternates between variational inference and Empirical Bayes to cleanly
distinguish variational and prior parameters. Using the VMM in a Variational
Autoencoder attains highly competitive clustering performance on benchmark
datasets. Augmenting scVI (Lopez et al., 2018), a popular scRNA-seq integration
method, with the VMM significantly improves its performance and automatically
arranges cells into biologically meaningful clusters.

对于深度潜在变量模型 (DLVMs)，当前的聚类先验方法要求事先定义聚类数目并容易受到初始值的影响。通过同时进行整合和聚类，我们将 VampPrior（Tomczak 和 Welling，2018）调整到一个狄利克雷过程高斯混合模型中，形成了 VampPrior Mixture Model（VMM），这是一个新的 DLVMs 先验方法。我们提出了一个交替使用变分推断和经验贝叶斯的推理过程，以清晰区分变分参数和先验参数。使用 VMM 在基准数据集上的变分自编码器获得了极具竞争力的聚类性能。将 VMM 与流行的 scRNA-seq 整合方法 scVI（Lopez 等，2018）相结合，可以显著提高其性能并自动将细胞分组成具有生物学意义的聚类。