NetChop - 3.1

Proteasomal cleavages (MHC ligands)

The NetChop server produces neural network predictions for cleavage sites of the human proteasome.

NetChop has been trained on human data only, and will therefore presumably have better performance for prediction of the cleavage sites of the human proteasome. However, since the proteasome structure is quite conserved, we believe that the server is able to produce reliable predictions for at least the other mammalian proteasomes.

This server is an update to the Netchop 2.0 server. It has been trained using a novel sequence encoding scheme, and an improved neural network training strategy. The Netchop 3.0 version has two different network methods that can be used for prediction. C-term 3.0 and 20S 3.0.

C-term 3.0 network is trained with a database consisting of 1260 publicly available MHC class I ligands (using only C-terminal cleavage site of the ligands). 20S network is trained with in vitro degradation data published in Toes, et al. and Emmerich et al. C-term 3.0 network performs best in predicting the boundaries of CTL epitopes.

Another proteasome prediction server is available in Tubingen University: PAProc


Correspondence:        Technical Support: