Fig. 3
From: SAE-Impute: imputation for single-cell data via subspace regression and auto-encoders
Assessment of SAEImpute, SAVER, AutoImpute, MAGIC, ScRecover, and ScImpute through simulation studies. The mean absolute error (MAE) was computed by comparing the estimated data with the complete data. Across all analyses, SAEImpute consistently exhibited lower MAE values compared to the other methods