Format

Send to

Choose Destination
Nat Genet. 2018 Aug;50(8):1171-1179. doi: 10.1038/s41588-018-0160-6. Epub 2018 Jul 16.

Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk.

Author information

1
Lewis-Sigler Institute for Integrative Genomics, Princeton University, Princeton, NJ, USA.
2
Graduate Program in Quantitative and Computational Biology, Princeton University, Princeton, NJ, USA.
3
Flatiron Institute, Simons Foundation, New York, NY, USA.
4
Lewis-Sigler Institute for Integrative Genomics, Princeton University, Princeton, NJ, USA. ogt@cs.princeton.edu.
5
Flatiron Institute, Simons Foundation, New York, NY, USA. ogt@cs.princeton.edu.
6
Department of Computer Science, Princeton University, Princeton, NJ, USA. ogt@cs.princeton.edu.

Abstract

Key challenges for human genetics, precision medicine and evolutionary biology include deciphering the regulatory code of gene expression and understanding the transcriptional effects of genome variation. However, this is extremely difficult because of the enormous scale of the noncoding mutation space. We developed a deep learning-based framework, ExPecto, that can accurately predict, ab initio from a DNA sequence, the tissue-specific transcriptional effects of mutations, including those that are rare or that have not been observed. We prioritized causal variants within disease- or trait-associated loci from all publicly available genome-wide association studies and experimentally validated predictions for four immune-related diseases. By exploiting the scalability of ExPecto, we characterized the regulatory mutation space for human RNA polymerase II-transcribed genes by in silico saturation mutagenesis and profiled > 140 million promoter-proximal mutations. This enables probing of evolutionary constraints on gene expression and ab initio prediction of mutation disease effects, making ExPecto an end-to-end computational framework for the in silico prediction of expression and disease risk.

PMID:
30013180
PMCID:
PMC6094955
DOI:
10.1038/s41588-018-0160-6
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center