SurfacOmics: an R shiny application integrating variable Feature Selection for gene biomarker discovery using Elastic-Net Regularization

Affordable sequencing technologies have resulted in a rapid rise in genomic and proteomic data. As a result, a massive amount of data is being analyzed, and the outcomes must be summarized as relevant clinical biomarkers. One of the major challenges is enabling wet-lab researchers to make meaningful inferences from the data, even in the absence of expertise in pipeline development and statistical training. We present a user-friendly R shiny application, SurfacOmics, which allows the user to perform biomarker identification via penalized regression algorithms. It also enables researchers to choose a crucial binary variable, such as treatment or group, from the study design metadata to anticipate potential biomarkers. We have introduced a novel concept of scoring scheme to characterize potential biomarkers for prediction, prioritization, and ranking. The tool integrates Gene Ontology information for sub-cellular localization together with a manually curated knowledgebase to provide valuable insights on biological processes, molecular functions and antibody resources, offering a comprehensive view in a single interface.