Fig. 4
From: An accurate and robust imputation method scImpute for single-cell RNA-seq data
scImpute corrects dropout values and helps define cellular identity in the simulated data. a The first two PCs calculated from the complete data, the raw data, and the imputed data by scImpute, MAGIC, and SAVER. Numbers in the parentheses are the within-cluster sum of squares calculated based on the first two PCs. The within-cluster sum of squares is defined as \(\mathop {\sum}\nolimits_{k = 1}^3 {\kern 1pt} \mathop {\sum}\nolimits_{j = 1}^{50} \left\| {{\bf{y}}_{kj} - \overline {\bf{y}} _{k \cdot }} \right\|^2\), where \(\overline {\bf{y}} _{k \cdot } = \frac{{1}}{{50}}\mathop {\sum}\nolimits_{j = 1}^{50} {\bf{y}}_{kj}\) and y kj is a vector of length 2, denoting the first two PCs of cell j in cell type c k . b The expression profiles of the 810 true DE genes in the complete, raw, and imputed datasets
