Abstract—An approach for cancer molecular classification based on their gene expression profiles is proposed. Four subtypes of the small, round blue-cell tumors (SRBCTs) were classified in this research. The Bhattacharyya distance of each gene was used as the gene selection method to select the twelve preliminary good genes for the SRBCTs subtypes classification. We then developed a classification method based on a fuzzy neural network (FNN) and a three-level classification model. Using the twelve preliminary good genes we did 100,000 iterations for each experiment on each level by using the FNN. After the experiments we got the number of bad cases (BC) for each gene. By the number of BC we deleted the bad genes one by one by using the FNN. Finally, we selected four genes for the SRBCTs subtype classification with 100% classification accuracy.
Index Terms— SRBCTs, Bhattacharyya distance, gene expression profiles, fuzzy neural networks, gene selection
Cite: Xue W. Tian and Joon S. Lim, "Gene Selection for SRBCTs Subtype Classification Using Fuzzy Neural Network," Journal of Image and Graphics, Vol. 1, No. 3, pp. 134-137, September 2013. doi: 10.12720/joig.1.3.134-137
Copyright © 2012-2021 Journal of Image and Graphics, All Rights Reserved