Contact Info:
Inci CETINDIL
cetindil (at) cs (dot) ucr (dot) edu
My Research Interest:
Data Mining, Machine Learning, Computational Biology
Progress Report
My project topic is Gene Expression Analysis.
I read the project and I have decided to implement it with Java.
I downloaded the data and figured out how to compute correlation coeffitions. After calculating the correlation coeffitions, I will build the graph.
After I had computed the mean and standard deviation of each row, I saw that the results were not very accurate. So I changed my equations and used a recurrence relation to calculate them.
I normalized the data and then computed the correlation coefficients. If the absolute value of the correlation coefficient is greater than 0.85, I put an edge to the graph.
Peaks and clusters were found. I found 9 clusters and one of my clusters was the same with the sample. For each cluster I created a file and wrote the expression of each gene in the cluster to the file. Then I imported each file to Excel and drew the graphs. One of my graphs was the same with the sample graph.
I am reading some papers to figure out what other analysis can be done.