RNA splicing, in which different coding RNA, or exons, are joined together after noncoding regions, or introns, are removed, allows for a large array of RNA transcript isoforms with distinct sequences, and functions in tissue- and cell-type-specific patterns. Conversely, transcript isoform alterations can sensitively reflect dynamic changes in cellular states. Aberrant splicing is closely associated with major diseases, such as cancer. In a new study published in Nature Computational Science titled, “HELIX: a scalable model for predicting context-dependent regulation of RNA splicing and isoform usage,” researchers from the Chinese Academy of Sciences have developed an AI-driven framework that enables highly accurate prediction of RNA splicing and isoform usage by integrating genomic sequence features with tissue-specific RNA binding protein (RBP) expression profiles. The work offers valuable insights for splicing regulatory patterns, pathogenic variant interpretation, and precision medicine research. Isoform usage is jointly regulated by multiple layers of control, including regulatory elements, such as splicing enhancers and silencers on exons and introns, and tissue microenvironments. Scientists have been challenged to accurately characterize and predict RNA splicing and isoform usage across tissues, cell types, and disease states. The study’s AI framework, Hierarchical Explainable LSTM for Isoform eXpression (HELIX), overcomes the limitations of conventional approaches via a two-layer deep-learning architecture. First, the framework integrates DNA sequence information with the expression profiles of 1,499 RBPs. Long short-term memory (LSTM) networks are then employed to effectively capture the complex dependencies and competitive relationships among multiple splice sites. This design enables precise, reliable prediction of RNA splicing and transcript isoform usage. The model was trained and optimized on large-scale short- and long-read RNA-seq datasets covering 30 distinct human tissues, allowing…
