Comprehensive RNA-binding protein analyses and deep learning uncover genetic constraints and disease associations in protein-RNA interfaces (opens in new tab)
Her et al. expand the human RBP-RNA interactome resource to 286 proteins by using eCLIP. By training deep-learning models, they decode RBP-binding syntax to quantify selective constraints and variant impacts. Their findings reveal evolutionary pressures on RBP-binding sites and identify RBP-related pathogenic mechanisms in retinal diseases and other disorders.
Read the original article