DNA microarray expression analysis and data mining for blood cancer
School of Computer and Information Science
The paper systematically presents how to discover useful information based on the DNA microarray expression data collected from mouse experiments for the leukemia research. The BCR-ABL oncogene is the cause of Ph+ leukemia. The BCR gene, on chromosome 22, breaks either at exon 1, exon 12/13, or exon 19 and fuses to the c-ABL gene on chromosome 9 to form, respectively, three types of BCR-ABL chimerical gene: P190, P210, or P230. Each of the three forms of the BCR-ABL oncogene is associated with a distinct type of human leukemia. An introduction to knowledge discovery from microarray experimental datasets has been provided. Specifically, the fold change analysis is discussed, step by step, based on the microarray data obtained from the mouse experiments of P190, P210 and P230. Many soft computing methodologies, involving fuzzy sets, neural networks, genetic algorithms, rough sets, wavelets, and their hybridizations, have recently been suggested to provide approximate solutions at low cost, thereby speeding up the process.