IRIS Integrates Sparse Sequence, Experimental, and AI-Predicted Structures for Protein-RNA Affinity Prediction and Motif Discovery

Abstract

Protein-RNA interactions are fundamental to numerous cellular processes, yet quantitatively characterizing their binding specificity remains a major challenge. We present IRIS (Integrative RNA-protein interaction prediction Informed by Structure and sequence), a biophysical framework that integrates residue-level sequence and structural features without relying on large-scale affinity data to predict binding affinities and identify binding motifs. Applied across different protein-RNA systems, IRIS predicts relative binding free energies ({Delta}{Delta}G) with consistent correlations and competitive error metrics, and its performance is further improved by incorporating additional high-affinity sequences into the training set. By leveraging predicted structural complexes, IRIS reveals alternative binding modes not observed in experimental structures, extends applicability to systems lacking experimental protein-RNA complexes, and generates a library of favorable RNA-binding motifs at protein-RNA interfaces. Collectively, these results establish IRIS as a versatile framework that leverages increasingly accurate structural predictions to enable quantitative modeling and rational engineering of protein-RNA interactions.