New Study by TSYS School's Rahmatullah Roche and Researchers from Virginia Tech Presents Computational Protocol for Predicting Protein-RNA Interactions

Knowledge of protein-RNA interactions is critical to an understanding of cellular biology, with potential impact on drug design and discovery. Numerous computational methods that have been developed to predict the RNA interaction sites on protein or protein interaction sites on RNA have attained promising prediction performance. However, these methods do not capture the three-dimensional (3D) interactions between protein and RNA in Euclidean space, which convey finer-grained complex structural information. New research by TSYS School computer scientist Rahmatullah Roche and Virginia Tech's Sumit Tarafder and Debswapna Bhattacharya presents a protocol to predict three-dimensional protein-RNA complex structural models from their sequences using a deep learning-based approach named ProRNA3D-single. Roche and his colleagues first delineate detailed steps for predicting protein-RNA interaction maps by leveraging pretrained language models. Their study, which appears in a recent issue of STAR Protocols, then describes the procedure for generating the protein-RNA complex structure from the predicted interactions using optimization techniques. The authors illustrate in the study that, despite some limitations, ProRNA3D-single demonstrates robustness and resilience in prediction performance. They also indicate that their protocol has potential applications in host-virus interactions and drug design. "In future, we plan to extend the prediction pipeline to support multi-chain and multi-molecular complex structural prediction," Roche explained.