Table 2 Comparison of different retention time predictors. This table shows the squared correlation coefficient between observed and predicted normalized retention time of retention time prediction methods of Petritis et al. [13, 14] on the Petritis test set [14]. These values are compared to our method, the POBK, on the Petritis test set [14]. The second column gives the number of training sequences used. For the last two rows, subsets of the data were chosen randomly so that 100 respectively 200 training peptides were selected.

From: Statistical learning of peptide retention behavior in chromatographic separations: a new kernel-based approach for computational proteomics