NetPhospan 1.0 Server
Prediction of phosphorylation using convolutional neural networks (CNNs).
View the version history of this server. All previous versions are available online, for comparison and reference.
NetPhospan server predicts phophorylation from any human kinase of known sequence using convolutional neural networks (CNNs). The method is trained on more than 8,700 reported phosphorylation sites by 120 different human protein kinase from homo sapiens. Furthermore, the server admits custom kinases provided as full length sequences in FASTA format.
Version 1.0 has been trained using the method described in this paper
Predictions can be made for peptides of length 21.
Link to table (tab seperated) describing the training data Training data table
For publication of results, please cite:
A generic Deep Convolutional Neural Network framework for prediction of Receptor-ligand Interactions. NetPhosPan; Application to Kinase Phosphorylation prediction.
Kinase domain sequences were obtained from
Phosphorylated sequences were obtained from
Would you prefer to run NetPhospan at your own site? NetPhospan v. 1.0
is available as a stand-alone software package, with the same
functionality as the service above. Ready-to-ship packages
exist for the most common UNIX platforms. There is a
for academic users; other users are requested to contact
CBS Software Package Manager at
Scientific problems: Technical problems: