CellVGAE

CellVGAE is an unsupervised scRNA-seq analysis workflow with graph attention networks. CellVGAE uses the connectivity between cells (such as k-nearest neighbour graphs or KNN) with gene expression values as node features to learn high-quality cell representations in a lower-dimensional space, with applications in downstream analyses like (density-based) clustering, visualisation, gene set enrichment analysis and others. CellVGAE leverages both the variational graph autoencoder and graph attention networks to offer a powerful and more interpretable machine learning approach.