DisProt Predictor of Intrinsically Disordered Regions

Download: The VSL2 predictor package can also be downloaded here. You can choose whether to use computationally demanding features derived from PSI-BLAST profiles and/or secondary structure predictions. Here are some detailed instructions about how to setup it on your own machine.

Note: Due to available computational resources we can provide only a limited number of predictions per day. For the VL2, VL3, VL3H, and VSL2B predictors we can provide up to 100 predictions per IP address per day. The maximum length of a query sequence is limited to 5,000 residues. For the VL3E and VSL2P predictors, up to 10 queries no longer than 500 residues can be processed per IP address per day.

!!!!! We have been experiencing occasional problems with web-based prediction system. If you submit a prediction job and don't get a response within 24 hours, please contact our system administrator.

Input sequence:

Please enter the sequence (without the Fasta header) using the single-letter AA code.

Predictor: VL2 (linear, 4 models)

VL3 (neural network based)
VL3H (neural network based)
VL3E (neural network based)

VSL2B (using 26 sequence-based features only)
VSL2P (also using 22 additional PSI-BLAST profile based features)

Output Window Length:

E-mail address:

If an e-mail address is provided, the predictions will be sent by e-mail upon completion. This is especially encouraged for VL3E and VSL2P predictors, which can take several minutes to process a sequence.

Citation: For VL2 predictor please refer to:
Vucetic S., Brown C.J., Dunker A.K. and Obradovic Z., Flavors of protein disorder (2003). Proteins 52 (4); 573-584.
For VL3 and VL3H predictors please refer to:
Obradovic Z., Peng K., Vucetic S., Radivojac P., Brown C. and Dunker A.K., Predicting intrinsic disorder from amino acid sequence (2003). Proteins 53 (S6); 566-572.
For VL3, VL3H and VL3E predictors please refer to:
Peng K., Vucetic S., Radivojac P., Brown C. J. , Dunker A. K. and Obradovic Z., Optimizing Intrinsic Disorder Predictors with Protein Evolutionary Information (2005). Journal of Bioinformatics and Computational Biology 3 (1); 35-60.
For VSL2B and VSL2P predictors please refer to:
Peng K., Radivojac P., Vucetic S., Dunker A.K., and Obradovic Z., Length-Dependent Prediction of Protein Intrinsic Disorder, BMC Bioinformatics 7:208, 2006.
Obradovic Z., Peng K., Vucetic S., Radivojac P., and Dunker A.K., Exploiting Heterogeneous Sequence Properties Improves Prediction of Protein Disorder, Proteins 61(S7):176-182, 2005.
Contact us