Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: ccImpute: an accurate and scalable consensus clustering based algorithm to impute dropout events in the single-cell RNA-seq data

Fig. 4

The bar plots show Silhouette widths values across the datasets with clustering assignments corresponding to the labels and Euclidean distances between imputed cells data. This metric shows if the imputation of the zero values exclusively has improved the separation of the cell data in the multidimensional space. The range of possible values is in the interval \([-1,1]\), with a higher value indicating better performance. ccImpute is the best performing approach overall, with scImpute performing slightly better on the Pollen dataset and DCA on some simulated datasets showing varied values where constant values are expected due to the characteristics of the simulated data. scImpute, DCA, and DeepImpute only work with raw unnormalized datasets and cannot impute the Usoskin dataset. Further, scImpute and DrImpute timed out on the larger datasets

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us