A Novel Method for Cancer Gene Prediction Using Back Propagation Algorithm

Cancer is a dynamic disease, it has been estimated that a new genetic alteration occurs in one out of 10000 tumor cells at each cell division. This leads to an increasing number of genetic aberrations in cancer cells, some of which result in altered gene expression. These changes in gene ex-pression are at least partially responsible for the characteristic of a tumor or tumor-type. Genome-wide gene expression pro-files provide detailed “tumor signatures” and can potentially be used for molecular diagnosis and classification of tumors. Cancer is a complex family of diseases, from the view of molecular biology; cancer is a genetic disease resulting from abnormal gene expression. Cancer leads to all mortalities, making it the second leading cause of death in the United States. Early and accurate detection of cancer is critical to the well being of patients. Analysis of gene expression data leads to cancer identification and classification, which will facilitate proper treatment selection and drug development. Gene expression data sets for ovarian, prostate, and lung cancer were analyzed in this research. An integrated gene-search algorithm for genetic expression data analysis was proposed. This integrated algorithm involves a genetic algorithm and correlation-based heuristics for data preprocessing (on partitioned data sets) and data mining (decision tree and support vector machines algorithms) for making predictions. Knowledge derived by the proposed algorithm has high classification accuracy with the ability to identify the most significant genes.