Protein-RNA interactions are crucial for many cellular processes, such as protein synthesis and regulation of gene expression. Missense mutations that alter protein-RNA interaction may contribute to the pathogenesis of many diseases. Here, we introduce a new computational method PremPRI, which predicts the effects of single mutations occurring in RNA binding proteins on the protein-RNA interactions by calculating the binding affinity changes quantitatively. The multiple linear regression scoring function of PremPRI is composed of three sequence- and eight structure-based features, and is parameterized on 248 mutations from 50 protein-RNA complexes. Our model shows a good agreement between calculated and experimental values of binding affinity changes with a Pearson correlation coefficient of 0.72 and the corresponding root-mean-square error of 0.76 kcal·mol-1, outperforming three other available methods. PremPRI can be used for finding functionally important variants, understanding the molecular mechanisms, and designing new protein-RNA interaction inhibitors.
Keywords: Mutation; Protein–RNA interaction; binding affinity change; computational approach.