PGS

PGS (Penalized Grid Search) is a software tool that uses a penalized regression model and grid search method to analyze high-dimensional miRNA expression data with repeated measures. This tool was developed to address the limitations of univariate association testing or the site-by-site testing methods which may underutilize the longitudinal feature of the data, leading to less biologically meaningful results. PGS was compared to the SBS testing and showed smaller phenotype prediction errors and higher enrichment of phenotype-related biological pathways. PGS provides more accurate estimates and higher sensitivity than SBS testing with comparable specificities according to extensive simulations.