RASSF2 Under the Computational Microscope: Prediction of Destabilizing Missense Variants

Abstract

Simple Summary The inactivation of the RASSF2 gene has been implicated in multiple types of cancer, and predicting variants that could potentially lead to its destabilization is important. Here, we used, for the first time, comprehensive machine-learning methods to prioritize the most destabilizing nsSNPs on the protein structure and function. Our study reports missense variants that can potentially alter the structure, function, and interactions of RASSF2. These variants may serve as candidates for future functional investigations.