MTSplice predicts effects of genetic variants on tissue-specific splicing

Jun Cheng, Muhammed Hasan Çelik, Anshul Kundaje, Julien Gagneur

Research output: Contribution to journalArticlepeer-review

19 Scopus citations


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.

Original languageEnglish
Article number94
JournalGenome Biology
Issue number1
StatePublished - Dec 2021


Dive into the research topics of 'MTSplice predicts effects of genetic variants on tissue-specific splicing'. Together they form a unique fingerprint.

Cite this