DISpro 1.0: Prediction of disordered regions from protein sequences

Reference: 
J. Cheng, M. Sweredoski, P. Baldi, Accurate Prediction of Protein
Disordered Regions by Mining Protein Structure Data, 
Data Mining and Knowledge Discovery, vol. 11, no. 3, pp. 213-222, 2005.

Contact:
Jianlin Cheng
PhD candidate
School of Information and Computer Sciences
University of California Irvine
email: jianlinc@uci.edu

Copyright: 
	Free for academic/scientific use. 


Installation (Linux Version):

0. Install SSpro4.0 package first. Get it from: http://contact.ics.uci.edu/download.html. Very easy to install. 

1. unzip dispro1.0.tar.gz
	e.g. tar xzf  dispro1.0.tar.gz

2. change directory into dispro1.0 
	e.g. cd dispro1.0

3. edit configure.pl
	set dispro path ($install_dir) and SSpro4 path ($pspro_dir) to their installation directories.

4. run configure.pl
	e.g., ./configure.pl

Installation is done.

Check the integrity of the installation
	cd test
	../bin/predict_diso.sh seq.fasta test.out

	The result in test.out should be the same as seq.diso.
	Output format:
		line 1: sequence
		line 2: D -> disorer, O -> order
		line 3: The predicted disorder probabilities for each residues. 
			The binary predictions on line 2 are generated by
			setting the threshold to 0.5. 
			You can set different probability thresholds to make 
			your own disorder/order predictions. For instance, to
			increase the sensitivity of predictions, you can lower the
			threshold.


Scripts in bin subdirectory:

	predict_diso.sh: predict disordered residues 


Enjoy it!