The PepCleave-CD4 algorithm predicts peptides resulting from preprocessing cleavage step. For a given set of proteins, it provides all predicted peptides of a given length. The algorithm uses the sequence of the peptide and its two flanking positions.
The PepCleave-CD4 algorithm can use three different classifiers. The different classifiers were learnt using SVM either on different database sizes or different parameters with a different bias for sensitivity, specificity and accuracy.
Input and output format
The input format is Fasta. The output is a list of predicted epitopes and their score.