Discovery of Translation Regulatory Features and Cross-UTR Interactions through Precise Mapping of mRNA Ends and Machine Learning
Ontology highlight
ABSTRACT: Cis-regulatory elements within 5′ and 3′ untranslated regions (UTRs) are critical for controlling mRNA translation efficiency (TE) and stability, but their coordinated functions remain poorly understood due to their complexity and variability. Here, we combined polysome profiling and mRNA decay measurements with TIF-seq2 to determine TE and half-lives of transcript isoforms (TIFs) with precisely defined 5′ and 3′ ends. We extracted regulatory features, positional k-mers, secondary structure characteristics, and TE measurements to build a multifaceted input for machine learning (ML) modeling. The resulting models demonstrated strong predictive power and revealed several unexpected findings. Specifically, 3′UTR regulatory features had a greater influence on TE than 5′UTRs, and negative regulatory features are more prevalent than positive ones for both translation and stability. We identified novel regulatory motifs in both UTRs, some with positional bias. Interestingly, AU-rich sequences in the 3’UTR, including the polyA signal, were identified and validated as translation enhancers. Finally, we found a crosstalk between 5’ and 3’ UTR through specific regulatory hubs. Together, these findings expand the understanding of translation regulation and suggest that UTR regulatory features evolve primarily to fine-tune inherently robust translation machinery for balanced protein expression.
ORGANISM(S): Mus musculus
PROVIDER: GSE303288 | GEO | 2026/07/22
REPOSITORIES: GEO
ACCESS DATA