The transport of peptides to the endoplasmic reticulum by the transporter associated with antigen processing (TAP) is a necessary step towards determining CD8 T cell epitopes. In this work, we have studied the predictive performance of support vector machine models trained on single residue positions and residue combinations drawn from a large dataset consisting of 613 nonamer peptides of known affinity to TAP. Predictive performance of these TAP affinity models was evaluated under 10‐fold cross‐validation experiments and measured using Pearson's correlation coefficients (Rp). Our results show that every peptide position (P1–P9) contributes to TAP binding (minimum Rp of 0.26 ± 0.11 was achieved by a model trained on the P6 residue), although the largest contributions to binding correspond to the C‐terminal end (Rp = 0.68 ± 0.06) and the P1 (Rp = 0.51 ± 0.09) and P2 (0.57 ± 0.08) residues of the peptide. Training the models on additional peptide residues generally improved their predictive performance and a maximum correlation (Rp = 0.89 ± 0.03) was achieved by a model trained on the full‐length sequences or a residue selection consisting of the first 5 N‐ and last 3 C‐terminal residues of the peptides included in the training set. A system for predicting the binding affinity of peptides to TAP using the methods described here is readily available for free public use at http://imed.med.ucm.es/Tools/tapreg/. Proteins 2010. © 2009 Wiley‐Liss, Inc.