Deep-learning augmented RNA-seq analysis of transcript splicing

Nat Methods. 2019 Apr;16(4):307-310. doi: 10.1038/s41592-019-0351-9. Epub 2019 Mar 25.


A major limitation of RNA sequencing (RNA-seq) analysis of alternative splicing is its reliance on high sequencing coverage. We report DARTS (, a computational framework that integrates deep-learning-based predictions with empirical RNA-seq evidence to infer differential alternative splicing between biological samples. DARTS leverages public RNA-seq big data to provide a knowledge base of splicing regulation via deep learning, thereby helping researchers better characterize alternative splicing using RNA-seq datasets even with modest coverage.

Publication types

  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Alternative Splicing
  • Bayes Theorem
  • Deep Learning*
  • Epigenomics
  • Exons
  • Gene Expression Profiling
  • Gene Expression Regulation
  • Hep G2 Cells
  • High-Throughput Nucleotide Sequencing
  • Humans
  • K562 Cells
  • Models, Statistical
  • RNA / analysis*
  • RNA / genetics
  • RNA Splicing*
  • Reproducibility of Results
  • Sequence Analysis, RNA*
  • Signal Processing, Computer-Assisted


  • RNA