A Metaheuristic Technique for Cluster-Based Feature Selection of DNA Methylation Data for Cancer

Epigenetics is the study of phenotypic variations that do not alter DNA sequences. Cancer epigenetics has grown rapidly over past few years as epigenetic alterations exist in all human cancers. One these methylation; an process regulates gene expression and often occurs at tumor suppressor loci cancer. Therefore, studying this methylation may shed light on different functions cannot otherwise be interpreted using changes occur Currently, microarray technologies; such Illumina Infinium BeadChip assays; are used to extremely large number varying loci. At each site, a beta value (β) reflect intensity. clustering data from various types cancers lead discovery partitions can help objectively classify well identify relevant without user bias. This proposed Nested Big Data Clustering Genetic Algorithm (NBDC-GA); novel evolutionary metaheuristic technique perform cluster-based feature selection based sites. The efficacy NBDC-GA was tested real-world sets retrieved Genome Atlas (TCGA); cancer genomics program created by National Institute (NCI) Human Research Institute. performance then compared with recently developed Immuno-Genetic (IGA) same sets. outperformed IGA terms convergence performance. Furthermore, produced more robust configuration while simultaneously decreasing dimensionality features maximum 67% 94.5% for individual type collective cancer, respectively. also able two chromosomes highly contrasting methylations activities were previously linked