Skip to main content
Fig. 3 | BMC Systems Biology

Fig. 3

From: A fast and efficient count-based matrix factorization method for detecting cell types from single-cell RNAseq data

Fig. 3

Performance evaluation on human embryonic stem scRNA-seq data set, which contains 1018 cells in seven cell types. Different colors also represent different cell types. a-h These five figure display the clustering output of two dimension of tSNE using five matrix factorization methods(PCA, Nimfa, NMFEM, tSNE, ZIFA, pCMF, ZINB-WaVE, and scNBMF). f This figure shows NMI and ARI values which are from eight compared methods

Back to article page