Predicting effects of noncoding variants with deep learning-based sequence model.

TitlePredicting effects of noncoding variants with deep learning-based sequence model.
Publication TypeJournal Article
Year of Publication2015
AuthorsZhou, J, Troyanskaya, OG
JournalNat Methods
Volume12
Issue10
Pagination931-4
Date Published2015 Oct
ISSN1548-7105
KeywordsAlgorithms, Chromatin, Epigenomics, Genome, Human, Hepatocyte Nuclear Factor 3-alpha, Humans, Models, Genetic, Mutation, Polymorphism, Single Nucleotide, Quantitative Trait Loci, Regulatory Sequences, Nucleic Acid, RNA, Untranslated, Support Vector Machine, Transcription Factors
Abstract

<p>Identifying functional effects of noncoding variants is a major challenge in human genetics. To predict the noncoding-variant effects de novo from sequence, we developed a deep learning-based algorithmic framework, DeepSEA (http://deepsea.princeton.edu/), that directly learns a regulatory sequence code from large-scale chromatin-profiling data, enabling prediction of chromatin effects of sequence alterations with single-nucleotide sensitivity. We further used this capability to improve prioritization of functional variants including expression quantitative trait loci (eQTLs) and disease-associated variants. </p>

DOI10.1038/nmeth.3547
Alternate JournalNat. Methods
PubMed ID26301843
PubMed Central IDPMC4768299
Grant ListR01 GM071966 / GM / NIGMS NIH HHS / United States
R01 HG005998 / HG / NHGRI NIH HHS / United States
P50 GM071508 / GM / NIGMS NIH HHS / United States
T32 HG003284 / HG / NHGRI NIH HHS / United States