Figure 2.

The three-fold cross-validation procedure of Percolator. Percolator discriminates between correct and incorrect PSMs by dividing the PSMs into three equally sized subsets. The PSMs of each subset are processed by an SVM-classifier that learned from the other two subsets.

Granholm et al. BMC Bioinformatics 2012 13(Suppl 16):S3   doi:10.1186/1471-2105-13-S16-S3