Fig. 2From: VIPER: variability-preserving imputation for accurate gene expression recovery in single-cell RNA sequencing studiesCorrelation between the masked truth and imputed values by different methods in the data masking experiment. Rows represent the four different data sets (Grun, Cell Type, and Time Course, Shalek) used in the experiment. Columns represent masking percentage (2%, 5%, and 10%). Methods for comparison include DrImpute (blue), MAGIC (green), SAVER (pink), scImpute (purple), VIPER with elastic net selection (peach), and VIPER with lasso selection (dark blue). Boxplots show correlation values obtained from 10 masking replicates, where in each replicate we calculated the correlation for each cell in turn and plotted the median correlation value across cellsBack to article page