Genetic Feature Selection Using Dimensionality Reduction Approaches

The recent decade has witnessed great advances in microarray and genotyping technologies which allow genome-wide single nucleotide polymorphism (SNP) data to be captured on a single chip. As a consequence, genome-wide association studies require the development of algorithms capable of manipulating ultra-large-scale SNP datasets. Two SNP selection methods were proposed towards this goal. The first is a filtering technique using Independent Component Analysis (ICA) and the second is a multivariate regression approach based on a modified version of Fast Orthogonal Search (mFOS). 


Figure 1: The workflow of SNP selection using ICA          Figure 2: Flowchart of the application of mFOS for modeling the SNP values