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.


Type of input

Paste a single sequence or several sequences in FASTA format into the field below:

or submit a file in FASTA format directly from your local disk:

Peptide length 

Select species/loci

Select Allele (max 20 per submission) or type allele names (ie HLA-A01:01) separated by commas (and no spaces). Max 20 alleles per submission)

For list of allowed allele names click here List of MHC allele names.

or paste a single full length MHC protein sequence in FASTA format into the field below:

or submit a file containing a full length MHC protein sequence in FASTA format directly from your local disk:

Sort by affinity 

At most 5000 sequences per submission; each sequence not more than 20,000 amino acids and not less than 8 amino acids. Max 20 MHC alleles per submission.

The sequences are kept confidential and will be deleted after processing.


For publication of results, please cite:

The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: application to MHC-peptide binding
Zhang H, Lund O, Nielsen M. Bioinformatics. 2009 May 15;25(10):1293-9

PMID: 19297351       Full text


1. Specify the input sequences

All the input sequences must be in one-letter amino acid code. The allowed alphabet (not case sensitive) is as follows:

A C D E F G H I K L M N P Q R S T V W Y and X (unknown)

All the other symbols will be converted to X before processing.

The server allows for input in either FASTA or PEPTIDE format.

Note that for Peptide input, all peptides MUST of equal length.

The sequences can be input in the following two ways:

  • Paste a single sequence (just the amino acids) or a number of sequences in FASTA format or a list of peptides into the upper window of the main server page.

  • Select a FASTA or PEPTIDE file on your local disk, either by typing the file name into the lower window or by browsing the disk.

Both ways can be employed at the same time: all the specified sequences will be processed. However, there may be not more than 10 sequences in total in one submission. The sequences shorter than 15 or longer than 10000 amino acids will be ignored.

2. Customize your run

Select the allele(s) you want to make predictions for from the scroll-down menu (select multiple alleles using the ctrl key), or type in the allele names separated by commas (with out blank spaces).

Click the box Sort by affinity to have the output sorted by descending predicted binding affinity

3. Submit the job

Click on the "Submit" button. The status of your job (either 'queued' or 'running') will be displayed and constantly updated until it terminates and the server output appears in the browser window.

At any time during the wait you may enter your e-mail address and simply leave the window. Your job will continue; you will be notified by e-mail when it has terminated. The e-mail message will contain the URL under which the results are stored; they will remain on the server for 24 hours for you to collect them.


Main reference:

The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: application to MHC-peptide binding
Zhang H, Lund O, Nielsen M. Bioinformatics. 2009 May 15;25(10):1293-9

Center for Biological Sequence Analysis, Technical University of Denmark, DK-2800 Lyngby, Denmark

MOTIVATION: Receptor-ligand interactions play an important role in controlling many biological systems. One prominent example is the binding of peptides to the major histocompatibility complex (MHC) molecules controlling the onset of cellular immune responses. Thousands of MHC allelic versions exist, making determination of the binding specificity for each variant experimentally infeasible. Here, we present a method that can extrapolate from variants with known binding specificity to those where no experimental data are available.

RESULTS: For each position in the peptide ligand, we extracted the polymorphic pocket residues in MHC molecules that are in close proximity to the peptide residue. For MHC molecules with known specificities, we established a library of pocket-residues and corresponding binding specificities. The binding specificity for a novel MHC molecule is calculated as the average of the specificities of MHC molecules in this library weighted by the similarity of their pocket-residues to the query. This PickPocket method is demonstrated to accurately predict MHC-peptide binding for a broad range of MHC alleles, including human and non-human species. In contrast to neural network-based pan-specific methods, PickPocket was shown to be robust both when data is scarce and when the similarity to MHC molecules with characterized binding specificity is low. A consensus method combining the PickPocket and NetMHCpan methods was shown to achieve superior predictive performance. This study demonstrates how integration of diverse algorithmic approaches can lead to improved prediction. The method may also be used for making ligand-binding predictions for other types of receptors where many variants exist.

PMID: 19297351

Full text

Software Downloads


Correspondence:        Technical Support: