Imputation performance of MAGIC and sc-PHENIX imputation through different increasing combinations of parameters. Here, we show the precision, recall, and f1-score performance metrics for imputation using different combinations of parameters of knn, t, and PCA dimensions. We used Flt1 for NonNeu_Endo and NonNeu_SMC cell types, Chat for GABA_Vip cell type, Sst for GABA_Sst cell type, and Serpin11 for Gluta_L6B cell types. The differential expression for the imputed gene markers was set to Fold Change = 2.0 and FWRD = 0.05 using Tukey’s HSD (honestly significant difference). Note: To increase values for PCA, we set it to knn = 15 and t= 15. To increase values for t, we set it to knn = 15 and n_pca = 30. For increasing values of knn, we set t= 15 and PCA= 30, similar to that shown in Figure 6 and Figure S13. Note: Gene markers: Flt1 (vascular endothelial growth factor receptor 1), and Chat (Choline Acetyltransferase), Sst (Somatostatin), and Serpinb11 (Serpin Family B Member 11).