Predicting Protein-RNA Binding Sites Using Structural Information

RNA molecules play diverse functional and structural roles in cells: they function as messengers for transferring genetic information from DNA to proteins, as the primary genetic material in many viruses, as enzymes important for protein synthesis and RNA processing, and as essential and ubiquitous regulators of gene expression in living organisms. All of these functions depend on precisely orchestrated interactions between RNA molecules and specific proteins in cells. Understanding the molecular mechanisms by which proteins recognize and bind RNA is essential for comprehending the functional implications of these interactions, but the recognition" code" that mediates interactions between proteins and RNA is not yet understood [1]. In this study, we use machine learning algorithms for training classifiers to predict protein-RNA interfaces using information derived from the sequence. We develop a two-stage classifier, called Struct-SVM that takes into account structural information: in the first stage, the instances that correspond to the surface target residues (ie, target residues that are on the surface) are separated from those that correspond to the non-surface target residues; in the second stage, if the target residue is on the surface, the classifier returns a probability that this residue is an interface residue given the sequence features as input to the classifier; otherwise, if the target