Project

Biclustering gene expression data. Implement the "random projection" algorithm for biclustering gene expression data described in the following paper. Run the progr am and collect experimental data. How would you improve its performance?

Progress Log

  • Feb 3  : starting to read the paper
  • Feb 4  : Design the data structure for the project
  • Feb 6  : Starting to code the matrix class and function
  • Feb 13: Starting to code the algorithm biculster_C
  • Feb 14: Testing on N=1 to N=10 and alpha from 2 to 32
  • Feb 19: Starting to design the algorithm biculster_R
  • Feb 20:  Starting to code the algorithm biculster_R
  • Feb 21: Testing on N=1000, alpha = 4.
  • Feb 25: Testing on N=1000, alpha = 2.
  • Feb 27: Running too long, modify the code to make it faster.
  • Mar 2:  Testing different parameter for the algorithms

Experimental Results

Largest_Bicluster_C

Largest_Bicluster_C

Largest_Bicluster_R

Largest_Bicluster_R

Reference

Stefano Lonardi, Wojciech Szpankowski, Qiaofeng Yang, Finding biclusters by random projections (http://www.cs.ucr.edu/~qyang/papers/cpm04.pdf)