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

• Main Authors: Dina Hafez, Aslihan Karabacak, Sabrina Krueger, Yih-Chii Hwang, Li-San Wang, Robert P. Zinzen, Uwe Ohler
• Format: Article
• Language: English
• Published: BMC 2017-10-01
• Series: Genome Biology
• Subjects: Interpolated Markov model; Enhancer to target gene assignment; Gene expression; Drosophila melanogaster; Gene regulation; Machine learning
• Online Access: http://link.springer.com/article/10.1186/s13059-017-1316-x

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.