Developing computational approaches for predicting nucleic acid binding proteins and their targets
Nucleic acid binding proteins, and specifically DNA-binding proteins (DBPs) and RNA-binding proteins (RBPs), play a central role in all steps of the gene expression pathway, from RNA transcription via post-transcriptional regulation to protein translation. Understanding the complexity of gene expression regulation requires the identification of RBPs and DBPs, which are involved in these processes, and to define their binding sites. To address these challenges, we developed BindUP-Alpha, a machine learning-based algorithm for predicting nucleic acid-binding proteins based on protein structure models from AlphaFold.We also developed intRBP, a deep learning model trained on high-throughput RNA-binding data, which accurately predicts the targets of RNA-binding proteins.
