DFLpred - Disordered Flexible Linker predictor

DFLpred webserver

The server is designed for the prediction of disordered flexible linker (DFL). The server generates numeric score for each residue in the input protein sequence that quantifies putative propensity to form a DFL. Larger value of propensity denotes higher likelihood to form DFLs. It also provides putative binary annotations (a given residue is predicted either as a DFL or not a DFL) based on false positive rate = 0.05 using threshold on the propensity score = 0.18. Residues with propensity > 0.18 are assumed to form DFLs and otherwise they are assumed not to form DFLs.

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 5000 (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.


DFLpred accepts either single or multiple protein sequences. The input is limited to 5000 protein sequences. 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 where DFLpred normally takes less than one minute to predict 100 proteins with average size of 500 AAs.):

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


    Explanation of TRAINING and TEST dataset
  • Line 1: >protein ID
  • Line 2: protein sequence (1-letter amino acid encoding)
  • Line 3: annotations of disordered flexible linker (DFL) regions, where '1' denotes a DFL, '0' denotes a structured residue or disordered residue annotated with functions other than DFL, 'x' denotes a residues that lacks annotation.


DFLpred is also provided as a stand-alone package written in Java, please see https://fanchi.github.io/DFLpred/ for details.


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

  • IUPred - Prediction of Intrinsically Unstructured Proteins
  • AAindex - Amino acid indices, substitution matrices and pair-wise contact potentials