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

• Published in: Nature communications Vol. 16; no. 1; pp. 1275 - 10
• Main Authors: Clauwaert, Jim, McVey, Zahra, Gupta, Ramneek, Yannuzzi, Ian, Basrur, Venkatesha, Nesvizhskii, Alexey I., Menschaert, Gerben, Prensner, John R.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 02.02.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 101/58; 49/91; 631/114/1305; 631/337/574/1789; 692/4028/67/2332; Biological activity; Brain; Brain - metabolism; Brain cancer; Cancer; Data analysis; Deep Learning; Deregulation; Humanities and Social Sciences; Humans; Machine learning; Medulloblastoma; Medulloblastoma - genetics; Medulloblastoma - metabolism; multidisciplinary; Open reading frames; Open Reading Frames - genetics; Protein biosynthesis; Protein Biosynthesis - genetics; Protein synthesis; Ribonucleic acid; Ribosomes - genetics; Ribosomes - metabolism; RNA; RNA, Messenger - genetics; RNA, Messenger - metabolism; Science; Science (multidisciplinary); Sensitivity analysis; Transcription; Translation
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-025-56543-0

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