Fig. 5
From: Bayesian model selection reveals biological origins of zero inflation in single-cell transcriptomics
Estimating zero inflation with a ZINB model. Zero inflation probability \(\widehat {\pi }_{0}\) estimated by ZINB on simulated NB data before cell type adjustment (a) and after cell type adjustment (b). Since simulated NB data does not contain zero inflation, it is implicit that the ZINB model should produce estimates of \(\widehat {\pi }_{0}\) that are zero or very small. However, we find substantial overestimation of this quantity for many simulated genes. Scatterplots of true versus estimated zero inflation \(\widehat {\pi }_{0}\) by ZINB on simulated ZINB data before cell type adjustment (c) and after cell type adjustment (d). Once cell type heterogeneity is regressed out, zero inflation is reduced