A new dimension in protein-RNA interface prediction: Integrating protein language models and geometric deep learning.

RNA-binding proteins (RBPs) are essential across biology, from viruses to complex multicellular organisms. They regulate gene expression and cellular responses, making RNA recognition central to understanding health and disease. Biochemical, biophysical, and structural studies have defined core principles of RNA binding, but recent RNA interactome surveys have expanded the RBP repertoire and revealed many noncanonical RNA-binding regions. This diversity demands highly scalable predictive methods. Here, we review machine learning predictors built on protein language models and structure-aware representations. These approaches improve generalisability, reduce reliance on deep evolutionary information, and enable proteome-scale prediction of RNA-binding residues, providing a route to map and interpret the molecular logic of protein-RNA interactions.