Decoding UTRs by applying explainable AI to a genomic foundation model

BackgroundThe regulation of mRNA decay and translation is crucial for cellular function and development; however, the complex interplay of RNA-binding proteins (RBPs) regulating these processes remains incompletely understood. Recent advances in genomic foundation models present new opportunities for decoding the regulatory grammar embedded within mRNA untranslated regions (UTRs). Here, we leverage explainable artificial intelligence to systematically identify RBP motifs that influence translation and mRNA decay during Drosophila melanogaster development. ResultsWe extended the training of GENA-LM Fly, a genomic foundation model, on all 5 and 3 UTR pairs from the D. melanogaster genome. We separately fine-tuned it using ribosome density (RD) and mRNA decay (half-life) data from the embryonic maternal-to-zygotic transition (MZT). Using SHapley Additive exPlanations (SHAP) analysis, we identified the sequence regions most influential for prediction and performed motif enrichment analysis to discover associated RBP binding sites. We identified 42 unique RBPs associated with increasing (n=23; e.g., Rnp4f, Mxt) or decreasing (n=19; e.g., Aret/Bruno, Rox8, Sxl, Orb2) RD and 18 unique RBPs associated with increasing (n=6) and decreasing (n=12; e.g., Cnot4, Rbp9, Rox8) mRNA half-life. Using publicly available PAR-CLIP data, we validated our Orb2 signal in a Drosophila cell line. Furthermore, feature ablation and shuffling experiments revealed the contributions of different sequence components to model performance. Our approach significantly outperformed naive high-versus-low RD comparisons, demonstrating the power of model explainability in biological discovery. ConclusionsThis study demonstrates that genomic foundation models, when combined with explainability methods, can discover meaningful biology even without drastically improving the underlying prediction accuracy. The identified RBP motifs provide new insights into post-transcriptional regulatory elements that govern RD and decay during early development.