Fast orthogonal search for genetic feature selection

In this paper, we present the application of a multivariate regression approach, fast orthogonal search, to select the most informative features in Single Nucleotide Polymorphism data, and to use these features to accurately model the entire data. Our results on two published datasets show very high accuracies in capturing the hidden information in the sequence of studied SNPs. The execution time for our developed methodology is very short and paves the way for its application to large-scale genome wide datasets.