IUPforest-L: Predicting Long Disordered Regions in
Proteins Using Random Forests

IUPforest-L is designed for batch prediction of long disordered regions in proteins. For prediction of a single protein sequence, please see related work.
Please upload a file (max 100KB) containing your query sequences in FASTA format.
The URL for the prediction result will be sent to you via email and result will be kept on our server for at least 3 days.
The prediction result for the complete eukaryotic proteomes can be found here .
Our blind test dataset Han-ADS1.fasta is here. The ReadMe file is here.
Options: Query sequences may contain many long disordered regions.
Query sequences may contain only a few long disordered regions.
False positive rate:
User Information: Institution:

Email Address:
IUPforest-L has been visited times. For comments and suggestions please email dmg@cs.rmit.edu.au.


The paper Predicting disordered regions in proteins using Random Forest is under review.

Han, P., Zhang, X., Norton, R. S. and Feng, Z. P. Predicting disordered regions in proteins based on decision trees of reduced amino acid composition. Journal of Computational Biology. 13(9): 1579-1590. 2006.

Breiman, L. Random forests. Machine Learning, 45: 5-32. 2001.

Hegger, R., Kantz. H. and Schreiber. T. Practical implementation of nonlinear time series methods: the TISEAN package. CHAOS.
9: 413. 1999.

Schreiber, T and Schmitz, A. Surrogate time series. Physica D. 142: 346. 2000.