SAFE-clustering: Single-cell Aggregated (From Ensemble) Clustering for Single-cell RNA-seq Data

SAFE-clustering is a flexible, accurate and robust method for clustering scRNA-seq data. SAFE-clustering takes as input results from multiple clustering methods to build one consensus clustering. Specifically, in our current implementation, single cells are first clustered using four state-of-the-art methods, SC3, CIDR, Seurat and t-SNE + k-means; individual solutions are then ensembled using three hypergraph-based partitioning algorithms, namely hypergraph partitioning algorithm (HGPA), meta-cluster algorithm (MCLA) and cluster-based similarity partitioning algorithm (CSPA). The current version is a pre-release. For details, please refer to our tutorial.

Comments and suggestions are welcome, please e-mail Yuchen Yang at yyuchen@email.unc.edu or Yun Li at yunli@med.unc.edu.