Cargando…

Sequential regulatory activity prediction across chromosomes with convolutional neural networks

Models for predicting phenotypic outcomes from genotypes have important applications to understanding genomic function and improving human health. Here, we develop a machine-learning system to predict cell-type–specific epigenetic and transcriptional profiles in large mammalian genomes from DNA sequ...

Descripción completa

Detalles Bibliográficos
Autores principales: Kelley, David R., Reshef, Yakir A., Bileschi, Maxwell, Belanger, David, McLean, Cory Y., Snoek, Jasper
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Cold Spring Harbor Laboratory Press 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5932613/
https://www.ncbi.nlm.nih.gov/pubmed/29588361
http://dx.doi.org/10.1101/gr.227819.117
_version_ 1783319849077833728
author Kelley, David R.
Reshef, Yakir A.
Bileschi, Maxwell
Belanger, David
McLean, Cory Y.
Snoek, Jasper
author_facet Kelley, David R.
Reshef, Yakir A.
Bileschi, Maxwell
Belanger, David
McLean, Cory Y.
Snoek, Jasper
author_sort Kelley, David R.
collection PubMed
description Models for predicting phenotypic outcomes from genotypes have important applications to understanding genomic function and improving human health. Here, we develop a machine-learning system to predict cell-type–specific epigenetic and transcriptional profiles in large mammalian genomes from DNA sequence alone. By use of convolutional neural networks, this system identifies promoters and distal regulatory elements and synthesizes their content to make effective gene expression predictions. We show that model predictions for the influence of genomic variants on gene expression align well to causal variants underlying eQTLs in human populations and can be useful for generating mechanistic hypotheses to enable fine mapping of disease loci.
format Online
Article
Text
id pubmed-5932613
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Cold Spring Harbor Laboratory Press
record_format MEDLINE/PubMed
spelling pubmed-59326132018-05-31 Sequential regulatory activity prediction across chromosomes with convolutional neural networks Kelley, David R. Reshef, Yakir A. Bileschi, Maxwell Belanger, David McLean, Cory Y. Snoek, Jasper Genome Res Method Models for predicting phenotypic outcomes from genotypes have important applications to understanding genomic function and improving human health. Here, we develop a machine-learning system to predict cell-type–specific epigenetic and transcriptional profiles in large mammalian genomes from DNA sequence alone. By use of convolutional neural networks, this system identifies promoters and distal regulatory elements and synthesizes their content to make effective gene expression predictions. We show that model predictions for the influence of genomic variants on gene expression align well to causal variants underlying eQTLs in human populations and can be useful for generating mechanistic hypotheses to enable fine mapping of disease loci. Cold Spring Harbor Laboratory Press 2018-05 /pmc/articles/PMC5932613/ /pubmed/29588361 http://dx.doi.org/10.1101/gr.227819.117 Text en © 2018 Kelley et al.; Published by Cold Spring Harbor Laboratory Press http://creativecommons.org/licenses/by/4.0/ This article, published in Genome Research, is available under a Creative Commons License (Attribution 4.0 International), as described at http://creativecommons.org/licenses/by/4.0/.
spellingShingle Method
Kelley, David R.
Reshef, Yakir A.
Bileschi, Maxwell
Belanger, David
McLean, Cory Y.
Snoek, Jasper
Sequential regulatory activity prediction across chromosomes with convolutional neural networks
title Sequential regulatory activity prediction across chromosomes with convolutional neural networks
title_full Sequential regulatory activity prediction across chromosomes with convolutional neural networks
title_fullStr Sequential regulatory activity prediction across chromosomes with convolutional neural networks
title_full_unstemmed Sequential regulatory activity prediction across chromosomes with convolutional neural networks
title_short Sequential regulatory activity prediction across chromosomes with convolutional neural networks
title_sort sequential regulatory activity prediction across chromosomes with convolutional neural networks
topic Method
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5932613/
https://www.ncbi.nlm.nih.gov/pubmed/29588361
http://dx.doi.org/10.1101/gr.227819.117
work_keys_str_mv AT kelleydavidr sequentialregulatoryactivitypredictionacrosschromosomeswithconvolutionalneuralnetworks
AT reshefyakira sequentialregulatoryactivitypredictionacrosschromosomeswithconvolutionalneuralnetworks
AT bileschimaxwell sequentialregulatoryactivitypredictionacrosschromosomeswithconvolutionalneuralnetworks
AT belangerdavid sequentialregulatoryactivitypredictionacrosschromosomeswithconvolutionalneuralnetworks
AT mcleancoryy sequentialregulatoryactivitypredictionacrosschromosomeswithconvolutionalneuralnetworks
AT snoekjasper sequentialregulatoryactivitypredictionacrosschromosomeswithconvolutionalneuralnetworks