flDPnn
(putative function- and linker based Disorder Prediction using deep neural network)

flDPnn is a webserver that predicts disorder using an innovative deep neural network that uses predictions of disorder functions and disordered linkers as inputs.

Please follow the three steps below to make predictions:

1. Copy and paste protein sequence(s) into text area

The server accepts up tp 20 FASTA formatted protein sequences with minimum length of 21 residues. Please enter protein sequence(s) in the following text field.

2. Provide your email address (optional)

Please enter your email address in the following text area or leave it blank. A link to prediction results will be sent to your email address once they are ready.

3. Predict

Click button to launch prediction.

Help

The webserver accepts up to 20 protein sequences as the input. The user should submit each protein sequence in the FASTA format.

The format of the input file is as follows:

  • Line1: >protein ID
  • Line2: protein sequence (1-letter amino acid encoding)

Here is an example input file.

Standalone version

    Standalone version can be found using the following links:
  • Source code: Click here to download
  • Docker container: Click here to download

Materials

    Datasets and Supporting Information
  • Training set: Click here to download
  • Validation set : Click here to download
  • Test set : Click here to download

Acknowledgments

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

  • PSI-BLAST-Protein sequence similarity search
  • IUPred- Prediction of intrinsic disorder
  • PSIPRED-Prediction of secondary structure
  • DisoRDPbind-Prediction of disordered RNA, DNA and protein binding regions
  • DFLpred-Prediction of disordered flexible linkers
  • fMoRFpred-Prediction of molecular recognition features

Updates

  • 2021 December - Updated residue numbers in the output visualization. Updated output csv format.
  • 2021 March - Initial release.