Web page for Math 501 Project, Spring 2007

Analysis of micro array gene expression data for cancer detection


Last update August 10, 2007 by Nasser Abbasi


This web page contains an archive of all the material I used when working on my project for Math 501, spring 2007 at CSUF. This web site also includes all material used when working on a paper with Professor Lee, C.H, Math dept. at CSUF. The paper was a conference paper titled Feature Extraction Techniques on DNA Microarray Data FOR Cancer Detection and was submitted to WACBE world congress on bioengineering 2007 at Bangkok, THAILAND.


Project Material


  1. This is an update made on June 30, 2007: I generated new results to compare using PCA and ICA for accuracy of cancer detection on the same data. This is not part of the paper that was sent to the conference but something that was done later.  This is the PDF file that contains this result. The matlab file I wrote was changed to add calls to do ICA using function written before by Michael Vodhanel which implements ICA. This zip file contains the matlab files needed. 

  2. The paper is here [WORD,  PDF,  HTML]


  1. This report contains another accuracy report I was working on before the paper above was completed. I include here as a reference. [WORD, PDF, HTML]


  1. My project review I've written while working on this is here [WORD, HTML]


  1. My Project scratch notes file. This contains many notes and links collected during working on this project. [WORD,  PDF, HTML]


  1. The project powerpoint presentation used in class is here [PPT,  PDF  , HTML]  and all the material used to make these power points are in this zip file. [ZIP] (6MB)


  1. I started working on a longer report in Latex, but ran out of time, so I switched to the power point presentation I did above. But here are the few pages I wrote. May be one day I'll finish this up and clean it more: [PDF,  HTML]

  2. This zip file contains miscellaneous VISIO drawings I've made during working on the project. [ZIP]

  3. This zip file contains old Peterson CD that Dr Lee gave me to work from. I keep here as a reference. It contains copies on papers and original matlab code written before. [Peterson_CD.zip]  (35 MB)

  4. These 2 papers are Chen et all papers in which we used the same data. Here they are for reference. chen_2002_liver_paper_1929.pdf and  chen_2003_gastric_paper_1929.pdf

  5. This zip file contains fastICA matlab implementation. Version 2.5. I did not use this, but may be in the future this can be used. FastICA_2.5.zip


  1. Description of the source code, how to run it, and data files needed to run the Matlab code is all described here [HTML]