Structure-aware Graph Learning Predicts RNA Editability Across Tissues and Species

Programmable A-to-I RNA editing using endogenous ADAR enzymes is emerging as a therapeutic strategy, but editability remains difficult to predict because ADAR recognition depends on double-stranded RNA geometry and stability rather than sequence alone. We present A dar E dit , a structure-explicit graph-attention framework that represents each dsRNA substrate as a nucleotide graph with backbone and base-pair edges and augments this representation with typed interactions and a motif-sensitive sequence branch. We trained and evaluated the model on high-confidence inverted <i>Alu</i> duplexes ( <i>n</i> = 905) with secondary structures predicted by RNAfold and editing levels measured across 8,603 GTEx RNA-seq samples spanning 47 tissues. Across five tissue contexts and comprehensive cross-tissue transfer experiments, A dar E dit consistently outperformed sequence-only CNN, transformer, and RNA language model baselines and achieved strong discrimination on combined tissue data (AUROC/AUPRC = 0.96; F1 ≈ 0.90). The same graph representation transferred to evolutionarily distant non- <i>Alu</i> species (sea urchin, acorn worm, and octopus), indicating conserved principles of ADAR substrate recognition. Finally, attention profiles and <i>in silico</i> mutagenesis recapitulated known biochemical constraints, including suppression by an upstream guanosine, and revealed longer-range asymmetric structural influences on editing. The sources of this work are available at our repository: https://github.com/Scientific-Computing-Lab/AdarEdit.