Format

Send to

Choose Destination
Genome Biol. 2017 Oct 26;18(1):199. doi: 10.1186/s13059-017-1316-x.

McEnhancer: predicting gene expression via semi-supervised assignment of enhancers to target genes.

Author information

1
Department of Computer Science, Duke University, Durham, 27708, NC, USA.
2
Berlin Institute for Medical Systems Biology, Max Delbrück Center for Molecular Medicine, Berlin, 13125, Germany.
3
Genomics and Computational Biology Graduate Program, University of Pennsylvania, Philadelphia, 19104, PA, USA.
4
Berlin Institute for Medical Systems Biology, Max Delbrück Center for Molecular Medicine, Berlin, 13125, Germany. Robert.Zinzen@mdc-berlin.de.
5
Department of Computer Science, Duke University, Durham, 27708, NC, USA. Uwe.Ohler@mdc-berlin.de.
6
Berlin Institute for Medical Systems Biology, Max Delbrück Center for Molecular Medicine, Berlin, 13125, Germany. Uwe.Ohler@mdc-berlin.de.
7
Departments of Biology and Computer Science, Humboldt University, Berlin, 10099, Germany. Uwe.Ohler@mdc-berlin.de.

Abstract

Transcriptional enhancers regulate spatio-temporal gene expression. While genomic assays can identify putative enhancers en masse, assigning target genes is a complex challenge. We devised a machine learning approach, McEnhancer, which links target genes to putative enhancers via a semi-supervised learning algorithm that predicts gene expression patterns based on enriched sequence features. Predicted expression patterns were 73-98% accurate, predicted assignments showed strong Hi-C interaction enrichment, enhancer-associated histone modifications were evident, and known functional motifs were recovered. Our model provides a general framework to link globally identified enhancers to targets and contributes to deciphering the regulatory genome.

KEYWORDS:

Drosophila melanogaster; Enhancer to target gene assignment; Gene expression; Gene regulation; Interpolated Markov model; Machine learning; Semi-supervised model

PMID:
29070071
PMCID:
PMC5657048
DOI:
10.1186/s13059-017-1316-x
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for BioMed Central Icon for PubMed Central
Loading ...
Support Center