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

The biological process of RNA translation is fundamental to cellular life and has wide-ranging implications in human disease. Yet, accurately delineating the variation in RNA translation represents a significant challenge. Here, we develop RIBO-former, a transformer model-based approach to map global RNA translation. We find that RIBO-former offers unparalleled precision and sensitivity for ribosome profiling data. Application of RIBO-former to normal brain and medulloblastoma enables high-resolution insights into disease regulation of RNA translation.

RNA翻译的生物学过程是细胞生命活动的核心基础，其与人类多种疾病存在广泛关联。然而，精准刻画RNA翻译的变异特征仍是一项极具难度的挑战。本研究开发了RIBO-former——一种基于Transformer模型的全局RNA翻译图谱绘制方法。研究表明，RIBO-former对核糖体谱（ribosome profiling）数据具备无与伦比的精确度与灵敏度。将RIBO-former应用于正常脑组织与髓母细胞瘤样本，可实现对RNA翻译疾病调控机制的高分辨率解析。