This paper shows that many deep learning models for RNA secondary structure prediction learn dataset bias more readily than RNA folding rules, and explains why that matters for the future of AI in RNA biology.
A comparative analysis of Musashi binding element accessibility in Zika virus and related flavivirus 3' UTRs using thermodynamic RNA structure modeling.
A landscape-based method for modeling how cotranscriptional folding and ligand binding interact in kinetically controlled riboswitches, illustrated with the 2'dG riboswitch from Mesoplasma florum.
A computational workflow for designing ligand-triggered RNA switches, with emphasis on sequence design, folding kinetics, and candidate prioritization.
This review explains how classical thermodynamic RNA folding models can be improved with chemical probing data, and why that combination remains one of the most reliable routes to biologically useful structure prediction.