Prediction for new epitopes

If your epitope of interest is not present in the TCRex database, you can train a custom prediction model yourself. This requires a training data set consisting of TCR beta sequences that are known to bind with your epitope of interest. Please make sure that this data set contains epitope-specific TCR beta sequences for only one epitope.

Your custom prediction model can be used to make TCR–epitope interaction predictions on new TCR beta sequences. Provide a TCR sequence file containing all TCR beta sequences for which you want to perform predictions as the target data set.

TCRex supports sequence data information in the TCRex format, the MiXCR format, and the immunoSEQ ANALYZER format (version 1 & 2).

Training data set

Attention: TCRex only supports training files with at most 500 TCR sequences.

Target data set

Attention: TCRex only supports prediction files with at most 50 000 TCR sequences.

TCRex is available for academic, non-personal research only. By using TCRex you agree to uphold and are bound by its terms and conditions.