Analysis and prediction of affinity of TAP binding peptides using cascade SVM

Abstract

The generation of cytotoxic T lymphocyte (CTL) epitopes from an antigenic sequence involves number of intracellular processes, including production of peptide fragments by proteasome and transport of peptides to endoplasmic reticulum through transporter associated with antigen processing (TAP). In this study, 409 peptides that bind to human TAP transporter with varying affinity were analyzed to explore the selectivity and specificity of TAP transporter. The abundance of each amino acid from P1 to P9 positions in high-, intermediate-, and low-affinity TAP binders were examined. The rules for predicting TAP binding regions in an antigenic sequence were derived from the above analysis. The quantitative matrix was generated on the basis of contribution of each position and residue in binding affinity. The correlation of r = 0.65 was obtained between experimentally determined and predicted binding affinity by using a quantitative matrix. Further a support vector machine (SVM)-based method has been developed to model the TAP binding affinity of peptides. The correlation (r = 0.80) was obtained between the predicted and experimental measured values by using sequence-based SVM. The reliability of prediction was further improved by cascade SVM that uses features of amino acids along with sequence. An extremely good correlation (r = 0.88) was obtained between measured and predicted values, when the cascade SVM-based method was evaluated through jackknife testing. A Web service, TAPPred (http://www.imtech.res.in/raghava/tappred/ or http://bioinformatics.uams.edu/mirror/tappred/), has been developed based on this approach.

Figure 1.

Diagrammatic representation of sequence-based SVM method.

Figure 2.

The schematic representation of cascade SVM–based prediction method. The prediction is performed by using two layers of SVM. In the first layer, prediction is based on the features and sequence information. At the second layer, prediction is based on the output of the first layer.

Figure 3.

The abundance and features of amino acids occurring in high-, intermediate-, and low-affinity binders at the first, second, third, and ninth positions. High, Intermediate, and Low specifies the high-, intermediate-, and low-affinity TAP binders. Positions 1, 2, 3, and 9 of TAP binders are specified by P1, P2, P3, and P9, respectively.

Figure 3.

The abundance and features of amino acids occurring in high-, intermediate-, and low-affinity binders at the first, second, third, and ninth positions. High, Intermediate, and Low specifies the high-, intermediate-, and low-affinity TAP binders. Positions 1, 2, 3, and 9 of TAP binders are specified by P1, P2, P3, and P9, respectively.

Figure 4.

Positional correlation between features of amino acids and TAP binding affinity of peptides. The correlation was obtained for nine features of amino acids, as discussed in Materials and Methods and shown by different graphs. The x-axes and y-axes in all graphs represent the peptide positions (P1 to P9) and correlation coefficient, respectively.