Skip to main content
. 2020 Jun 12;128(6):067010. doi: 10.1289/EHP6508

Figure 5.

Figure 5A is a graph, plotting predicted FC subscript IL-1 beta, ranging from negative 10 to 40 in increments of 10 (y-axis) across experimental FC subscript IC-1 beta, ranging from negative 10 to 40 in increments of 10 (x-axis) for training set and test set. Figure 5B is a graph, plotting O superscript asterisk, ranging from negative 4 to 4 in unit increments (y-axis) across h, ranging from 0.0 to 1.2 in increments of 0.2 (x-axis) for training set and test set, where h superscript asterisk equals 0.6.

Performance of the continuous model. (A) Plot of experimentally determined data (x-axis) vs. predicted fold change of IL-1β production (FCIL−1β) values (y-axis). The straight solid line represents perfect agreement between experimental and calculated values. Squares represent values predicted for the metal oxides (MeONPs) from the training set; triangles represent MeONPs from the test set. The distance of each symbol from the solid line corresponds to its deviation from the related experimental value. The dotted lines showing the range encompassing 90% of the predictions. (B) Model applicability domain: Williams plot of standardized residuals (σ*) vs. leverage values (hi) for FCIL−1β. MeONPs having hi>h* or |σ|>3 should be identified as outliers.