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

Instructions Output format Article abstract Download

SUBMISSION

Hover the mouse cursor over the symbol for a short description of the options

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:

Method Selection
Pan-specific method
Generic method

Select kinase group

Select Kinase (max 20 per submission) or type Kinase gene name (e.g. AKT1) separated by commas (and no spaces). (Max 20 kinases per submission)

For list of allowed kinase names click here List of Kinase gene names.

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

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



Sort by predicted score 

Save predictions to XLS file 

Restrictions:
At most 5000 sequences per submission; each sequence not more than 20,000 amino acids and not less than 8 amino acids. Max 20 kinase domains per submission.

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


CITATIONS

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.
Emilio Fenoy, Jose M. G. Izarzugaza, Vanessa Jurtz, Søren Brunak and Morten Nielsen.
Bioinformatics (2018).
Full text  


DATA RESOURCES

Kinase domain sequences were obtained from

  • KinBase database. Manning G, Whyte DB, Martinez R, Hunter T, Sudarsanam S. The protein kinase complement of the human genome. Science. 2002 Dec 6;298(5600):1912-34.

Phosphorylated sequences were obtained from

  • Phospho.ELM database. Craveur P, Rebehmed J, de Brevern AG; PTM-SD: a database of structurally resolved and annotated posttranslational modifications in proteins. Database (Oxford) 2014; 2014 bau041. doi: 10.1093/database/bau041.
  • PhosphositePlus database. Hornbeck PV, Zhang B, Murray B, Kornhauser JM, Latham V, Skrzypek E; PhosphoSitePlus, 2014: mutations, PTMs and recalibrations. Nucleic Acids Res 2015; 43 (D1): D512-D520. doi: 10.1093/nar/gku1267

PORTABLE VERSION

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 download page for academic users; other users are requested to contact CBS Software Package Manager at software@cbs.dtu.dk.


GETTING HELP

Scientific problems:        Technical problems: