Thesis (Ph.D.) - Cairo University - Faculty of Computers and Information - Department of Computer Science

Due to the fundamental role of the aberrant DNA methylation during a disease development such as cancer, the comprehension of its mechanism had become essential in the recent years for early detection and diagnosis. With the advent of the high-throughput technologies, there are still several challenges to achieve the classification process using the DNA methylation data. The high-dimensionality and high-noisiness of the DNA methylation data may lead to the degradation of the prediction accuracy. Thus, it becomes increasingly important in a wide range to employ robust computational tools such as feature selection and extraction methods to extract the informative features amongst thousands of them, and hence improving cancer prediction.This thesis aims at predicting cancer with a hybridized approach based on novel feature selection and feature extraction techniques.The hybridized approach uses the DNA methylation value in different regions, for example: promoters, genes, CpG Islands and probes

Issued also as CD