Documentation of SVMcon 1.0

SVMcon is a software to predict protein residue-residue contacts in 8 Angstrom distance threshold.
It is one of the most accurate contact predictors in the 7th and 8th editions of Critical Assessment of Techniques for Protein Structure Prediction (CASP7&8).
It is the only free contact map prediction software (including source code) available so far.


1. install secondary structure and solvent accessibility predictor PSpro (PSpro1.1 or PSpro2.0) (download it from: easy to install).

2. unzip svmcon.tar.gz

3. do configuration

cd svmcon
set $install_dir to svmcon directory
set $pspro_dir to PSpro directory (full path)
run ./ to configure.

installation is done.

Test Installation

cd test
../bin/ T0288.fasta

The output should be the same as

Run the program: fasta_file output_file

fasta_file: protein sequence in the simple FASTA foramt
(line1: >name; line 2: a plain protein sequence).

Output file includes the predicted residue contacts in CASP format.

Since there are lot of support vectors in the SVM model, it takes from
tens of minutes to several hours to predict contacts for a protein, depending
on sequence length.


J. Cheng and P. Baldi. Improved Residue Contact Prediction Using Support Vector Machines and a Large Feature Set. BMC Bioinformatics. 8:113, 2007.

Author: Jianlin Cheng, PhD. School of EECS, University of Central Florida.

Free for academic and scientific use only.
Copyright @ Jianlin Cheng
Please do not re-distribute the software without the permission of the author.

Jianlin Cheng at

Third-party software used by SVMcon

SVMcon softwre uses svm_classify program in SVM-light ( to classify data points.

Reference to SVM-light:

T. Joachims, 11 in: Making large-Scale SVM Learning Practical. Advances in Kernel Methods - Support Vector Learning, B. Sch?lkopf and C. Burges and A. Smola (ed.), MIT Press, 1999.

I thank the author of SVM-light (Dr. Thorsten Joachims) for the permit to include svm_classify in the SVMcon package.

Here is the license quoted from the SVM-light website:

SVM-light is free only for non-commercial use. It must not be distributed without prior permission of the author. The author is not responsible for implications from the use of this software.

National Institutes of Health (NIH) National Institute of General Medical Sciences (NIGMS) University of Missouri
This page last updated March 16, 2011
Bioinformatics and Systems Biology Laboratory, Department of Computer Science, University of Missouri