An RNA Language Model trained on sequence alone reveals the structural logic of Internal Ribosome Entry Sites

Picornaviruses initiate translation through Internal Ribosome Entry Sites (IRESes), RNA elements that recruit ribosomes independent of the 5` cap. These elements are large and highly divergent, and structural understanding remains limited to a handful of cases.

We address this bottleneck by introducing an RNA language model (Albatross), trained purely on sequence, that predicts high-quality IRES structures at scale. We collect \textit{in cellulo} chemical probing data for 96 full-length IRESes from divergent viruses and show that Albatross has high precision (median 0.77), outperforming co-variation analysis. Analyzing 75,000 IRES structures, we discover a novel Type II structural subclass and validate it experimentally.