Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: A convolutional neural network-based regression model to infer the epigenetic crosstalk responsible for CG methylation patterns

Fig. 4

Application of epiNet to other cell types. a The prediction of the CG methylation pattern of mouse embryonic stem (ES) cells, human ES cells, and human neuronal progenitor (NP) cells based on varying numbers of input features. For each number of features (N = 1, 2 or 5), the feature combination that showed the best correlation between the predicted and actual CG methylation patterns is shown. b–d Representative genome browser shots showing the predicted CG methylation patterns of mouse ES cells (b), human ES cells (c) and human NP cells (d). Together with the actual CG methylation pattern, the patterns of the two histone modifications responsible for the best prediction of CG methylation (H3K4me3 and either H3K27me3 or H3K36me3) are shown for comparison. Genomic regions in which H3K4me3 enrichment coincides with a local reduction of CG methylation are highlighted in yellow. RefSeq genes are shown at the bottom

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us