Deep learning to decode sites of RNA translation in normal and cancerous tissues

• DOI: 10.1038/s41467-025-56543-0
• Publication Date: 2025-02-02T11:30:07Z
• Authors: Jim Clauwaert; Zahra McVey; Ramneek Gupta; Ian Yannuzzi; Venkatesha Basrur; Alexey I. Nesvizh...; Gerben Menschaert; John R. Prensner
• Keywords: Ribosome profiling; Profiling (computer programming); ORFS; Eukaryotic translation

Abstract The biological process of RNA translation is fundamental to cellular life and has wide-ranging implications for human disease. Accurate delineation variation represents a significant challenge due the complexity technical limitations. Here, we introduce RiboTIE, transformer model-based approach designed enhance analysis ribosome profiling data. Unlike existing methods, RiboTIE leverages raw counts directly robustly detect translated open reading frames (ORFs) with high precision sensitivity, evaluated on diverse set datasets. We demonstrate that successfully recapitulates known findings provides novel insights into regulation in both normal brain medulloblastoma cancer samples. Our results suggest versatile tool can significantly improve accuracy depth Ribo-Seq data analysis, thereby advancing our understanding protein synthesis its