Multilayered Fusion-based Disorder predictor v. 2.00 (MFDp2)

MFDp2 webserver

MFDp2 combines per-residue disorder probabilities predicted by MFDp with per-sequence disorder content predicted by DisCon, and applies novel post-processing filters to provide disorder predictions with improved predictive quality. It outputs optimized per-residue disorder probability profiles, per-sequence disorder content, list (with analysis) of disordered segments, and several profiles that help in the interpretation of the results. The results are available online in graphical format and can be also downloaded in text-based (parsable) format.

Note: Result page enables the user to download the raw results from MFDp and DisCon as .csv or .fasta file if needed for comparison with other methods.

HINT: The symbols indicate availability of (additional) explanations. Clicking opens a new window with help and hints related to the selected section/task.

Please follow the three steps below to make predictions:

1. Upload a file with protein sequences, or paste them into text area

Server accepts up to 5 (FASTA formated) protein sequences. Either upload a file or enter each protein in a new line in the following text field (see Help for details):

2. Provide your e-mail address (required)

Please provide your e-mail address to be notified when results are ready.

3. Predict:

Click button to launch prediction.


  • DP_new - Dataset used to validate MFDp2 (each residue is annotated with one of the following O - ordered, D - disordered, u - unknow annotation)
  • MxD - Dataset used in Bioinformatics 2010 26(18): i489-i496.
  • MxD training, and MxD test - datasets used in BMC Bioinformatics, 2011 12(1): 245.
  • Appendix for Bioinformatics 2010 26(18): i489-i496.


We acknowledge with thanks the following software used as a part of this server: