A Nonparametric Multi-view Model for Estimating Cell Type-Specific Gene Regulatory Networks
This work addresses the challenge of interpreting cell clusters and regulatory networks in genomics, though it appears incremental as it builds on existing multi-view and Bayesian methods.
The authors tackled the problem of estimating cell type-specific gene regulatory networks by integrating single-cell gene expression and epigenetic data, resulting in a model that outperformed other methods on synthetic and real genomic data.
We present a Bayesian hierarchical multi-view mixture model termed Symphony that simultaneously learns clusters of cells representing cell types and their underlying gene regulatory networks by integrating data from two views: single-cell gene expression data and paired epigenetic data, which is informative of gene-gene interactions. This model improves interpretation of clusters as cell types with similar expression patterns as well as regulatory networks driving expression, by explaining gene-gene covariances with the biological machinery regulating gene expression. We show the theoretical advantages of the multi-view learning approach and present a Variational EM inference procedure. We demonstrate superior performance on both synthetic data and real genomic data with subtypes of peripheral blood cells compared to other methods.