GEE-TGDR: A Longitudinal Feature Selection Algorithm and Its Application to lncRNA Expression Profiles for Psoriasis Patients Treated with Immune Therapies

With the fast evolution of high-throughput technology, longitudinal gene expression experiments have become affordable and increasingly common in biomedical fields. Generalized estimating equation (GEE) approach is a widely used statistical method for analysis data. Feature selection imperative omics data analysis. Among variety existing feature methods, an embedded method—threshold gradient descent regularization (TGDR)—stands out due to its excellent characteristics. An alignment GEE with TGDR promising area purpose identifying relevant markers that can explain dynamic changes outcomes across time. We proposed new novel algorithm outcomes—GEE-TGDR. In GEE-TGDR method, corresponding quasilikelihood function model objective be optimized, optimization are accomplished by method. Long noncoding RNAs (lncRNAs) posttranscriptional epigenetic regulators lower levels more tissue-specific compared protein-coding genes. So far, implication lncRNAs psoriasis remains largely unexplored poorly understood even though some evidence literature supports highly associated. this study, we applied lncRNA dataset examined response patients immune treatments. As result, list including 10 was identified predictive accuracy 70% superior accuracies achieved two competitive methods meaningful biological interpretation. A widespread application anticipated.