DeepPRObind

Help | Materials | References | Acknowledgments

DeepPRObind webserver

DeepPRObind provides predictions of the protein interactions.

Please follow the three steps below to make predictions:

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

This webserver accepts up to 20 FASTA-formated protein sequences. See Help for details of the input.

2. Provide email address (optional)

Please provide your email address to be notified when results are ready(optional).

3. Predict:

Click button to launch prediction.

Help

The user should submit the protein sequence(s) in FASTA format.

The format of the input file is as follows (Here is an example of input file.)

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

Each protein requires two lines and multiple proteins should be placed in consecutive lines.

Materials

    Datasets used to design and evaluate DeepPRObind:
  • Training dataset: Click here to download
  • Test dataset: Click here to download
  • Prediction for the yeast proteome: Click here to download.

    • Supplementary materials for the DeepPRObind publication are available here.

Reference

Acknowledgments

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

  • IUPred2A - Prediction of intrinsically disordered regions and disorderd binding regions
  • PSIPRED - Prediction of secondary structure
  • ASAquick - Fast neural network-based predictor of solvent accessibility
  • HHBlits - Algorithm for homology detection by iterative HMM-HMM comparison