Fig. 2From: IPC – Isoelectric Point CalculatorCorrelation of the experimental versus theoretical isoelectric points calculated using different pKa sets. Data for the main protein dataset (merged dataset created from SWISS-2DPAGE and PIP-DB). R2 – Pearson correlation before the removal of outliers. R2corr – Pearson correlation after the removal of outliers. Additionally, the linear regression models fitted to predictions with outliers (magenta line) and without outliers (blue line) are shown. Outliers (marked in magenta) are defined as pI predictions with MSE > 3 in comparison to the experimental pI. Other predictions are represented as heat maps according to the density of points. The numbers of outliers for both the training and testing set are shown together. For brevity, only six pKa sets are shownBack to article page