CN Algorithm


In order to quantitatively evaluate the performance of the CN algorithm, we use simulated dataset which generated from Dream3 (Dialogue for Reverse Engineering Assessments and Methods) size of 10, 50 and 100 and real dataset (SOS DNA repair network with experiment data set in Escherichia coli).

 We proposed an algorithm (SORDER algorithm) which is a strategy to find suitable sequential order of genes considering the degree of vertices in the graph. Moreover results of SORDER algorithm showed the presence of dependency on the selected threshold for CMI tests. To construct a weighted graph, another algorithm called CN algorithm was introduced. In this algorithm, only when the weighted value of the existing edge between two vertices is greater than a defined threshold, the existence of relationship between them is considered.

SORDER and CN algorithms are written in Matlab. It gets simulated data and real data as inputs. This algorithm applied for learning the skeleton of Gene Regulatory Network.
In order to direct edges of resulted network by CN algorithm, CNMIT algorithm is introduced. CNMIT is written in Matlab and Java.


How To Run The Program:


1.      One file is available for download (Dataset.rar): These file contains the data sets and true networks.


2.      One file is available for download ( These file contains Matlab and JAVA codes for learning Gene Regulatory Network.

3.      Run the program for each data set.




  • Rosa Aghdam, University of Shahid Beheshti
  • Mojtaba Ganjali, University of Shahid Beheshti
  • Xiujun Zhang, Shanghai Institutes for Biological Sciences
  • Changiz Ezlahchi, Shahid Beheshti University


Contact Us

In the case that you have questions, suggestions or comments,

send email to





webmaster |   Copyright © 2014, All rights reserved.