HELIX: a scalable model for predicting context-dependent regulation of RNA splicing and isoform usage - PubMed
an hour ago
- #isoform usage
- #deep learning
- #RNA splicing
- HELIX is a hierarchical deep learning framework that predicts tissue- and condition-specific RNA splicing patterns and transcript isoform usage.
- It integrates pre-mRNA sequence and RNA-binding protein expression profiles, leveraging both short-read and long-read RNA sequencing data for training.
- HELIX outperforms existing models and methods in predicting differential splicing events, splicing strength, and isoform usage.
- The model enables identification of tissue-specific splicing quantitative trait loci (sQTLs) and their functional impacts.
- It predicts patient-specific splicing dysregulation in colon cancer, attributing it to genetic variants and abnormal RNA-binding protein expression.
- Through transfer learning, HELIX can be adapted to single-cell RNA sequencing data to predict cell-type-specific isoforms.