fMoRFpred - fast Molecular Recognition Feature predictor

References | Materials | Acknowledgments | Disclaimer | Biomine

fMoRFpred webserver

The server provides a fast version of protein Molecular Recognition Feature (MoRF) prediction. Comparing with our MoRFpred predictor, this server is built for more efficient online prediction with slightly compromising the prediction accuracy.

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 2000 (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.

References

Upon the usage the users are requested to use the following citation:

Materials

  • Supplement - Supplementary materials.
  • Training dataset - Dataset used to develop the method (to perform feature selection and parameterize the prediction algorithm) based on 5-fold cross validation protocol.
  • Test dataset - Dataset developed using PDB depositions from before April 2008, which is used to evaluate and compare our method with the existing predictors. Shares up to 30% similarity with the training dataset.
  • Experimental - Dataset developed using experimentally validated data extracted from publications between 2008 and 2012. Shares up to 30% similarity with the training dataset.
  • Test 2012 - Dataset developed using PDB depositions from 2012. Shares up to 30% similarity with the training dataset.
  • Negative dataset - Dataset developed using PDB depositions between January 2010 and March 2012, consisting of ordered apo structures.

The datasets come as FASTA like text file with three lines per protein. The first line contains the sequence id (PDB id of the Morf segment and Uniprot id of the parent sequence) and also the secondary structure of the MoRF region in the bound state. The second and third line correspond to AA sequence, and annotation of the MoRF residues (1 - MoRF, 0- non-MoRF) respectively.

Acknowledgments

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

  • IUpred - Prediction of intrinsically unstructured proteins
  • Espritz - Prediction of intrinsically disordered regions
  • PSIPRED - Protein secondary structure prediction