Affordable Access

Access to the full text

MTSplice predicts effects of genetic variants on tissue-specific splicing

Authors
  • Cheng, Jun1
  • Çelik, Muhammed Hasan1
  • Kundaje, Anshul2, 3
  • Gagneur, Julien1, 4, 5
  • 1 Department of Informatics, Technical University of Munich, Boltzmannstraße, Garching, 85748, Germany , Garching (Germany)
  • 2 Department of Computer Science, Stanford University, Stanford, CA, USA , Stanford (United States)
  • 3 Department of Genetics, Stanford University, Stanford, CA, USA , Stanford (United States)
  • 4 Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany , Neuherberg (Germany)
  • 5 Institute of Human Genetics, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany , Munich (Germany)
Type
Published Article
Publication Date
Mar 31, 2021
Volume
22
Issue
1
Identifiers
DOI: 10.1186/s13059-021-02273-7
Source
Springer Nature
License
Green

Abstract

We develop the free and open-source model Multi-tissue Splicing (MTSplice) to predict the effects of genetic variants on splicing of cassette exons in 56 human tissues. MTSplice combines MMSplice, which models constitutive regulatory sequences, with a new neural network that models tissue-specific regulatory sequences. MTSplice outperforms MMSplice on predicting tissue-specific variations associated with genetic variants in most tissues of the GTEx dataset, with largest improvements on brain tissues. Furthermore, MTSplice predicts that autism-associated de novo mutations are enriched for variants affecting splicing specifically in the brain. We foresee that MTSplice will aid interpreting variants associated with tissue-specific disorders.

Report this publication

Statistics

Seen <100 times