Fig. 1From: scConsensus: combining supervised and unsupervised clustering for cell type identification in single-cell RNA sequencing dataThe scConsensus workflow. a The scConsensus workflow considers two independent cell cluster annotations obtained from any pair of supervised and unsupervised clustering methods. b A contingency table is generated to elucidate the overlap of the annotations on the single cell level. A consensus labeling is generated using either an automated method or manual curation by the user. c DE genes are computed between all pairs of consensus clusters. Those DE genes are used to re-cluster the data. The refined clusters thus obtained can be annotated with cell type labelsBack to article page