PickPocket - 1.1

Binding of peptides to any known MHC class I molecule using binding pocket matrix extrapolation

PickPocket server predicts binding of peptides to any known MHC molecule using positiion specific weight matrices. The method is trained on more than 150,000 quantitative binding data covering more than 150 different MHC molecules. Predictions can be made for HLA-A, B, C, E and G alleles, as well as for non-human primates, mouse, Cattle and pig. Further, the user can upload full length MHC protein sequences, and have the server predict MHC restricted peptides from any given protein of interest.

Version 1.1 has been retrained on extented data set including 10 prevalent HLA-C and 7 prevalent BoLA MHC-I molecules.

The PSWM's are generated using the SMM_pmbec method described in 19948066

Predictions can be made for 8-12 mer peptides. Note, that all non 9mer predictions are made using approximations. Most HLA molecules have a strong preference for binding 9mers.

The prediction values are given in nM IC50 values.

The project is a collaboration between CBS, IMMI at Copenhagen university , and LIAI.

Link to table (tab seperated) describing the training data Training data table.

As of July 8th, the nomenclature for BoLA-I has been updated to follow IPD Release 1.3.


Correspondence:        Technical Support: