Enhancer prediction with histone modification marks using a hybrid neural network model

Enhancer is a DNA sequence of a genome that controls transcription of downstream target genes. Enhancers are known to be associated with certain epigenetic signatures. Machine learning tools, such as CSI-ANN, ChromHMM, and RFECS, were developed for predicting enhancers using various epigenetic features. However, predictions by different tools vary widely and quite a significant portion of enhancer predictions does not agree. Thus, computational methods for enhancer prediction should be further developed. In this paper, a hybrid neural network called Enhancer-CRNN, a convolutional neural network (CNN) followed by a recurrent neural network (RNN), was developed and they were used to predict enhancer regions with histone modification marks as input. The CNN in our model is to reflect local characteristics and the RNN is to learn sequential dependencies among the histone marks. Hybridization of both neural networks outperformed existing prediction tools in experiments with GM12878, H1hesc, HeLaS3, and HepG2 cell lines. On average, 13-17 percent of the enhancers predicted by our method were cell type-specific. With the trained model, optimized virtual input histone marks was generated to provide a deeper insight into how histone modification marks can represent enhancer regions in which histone marks indicate active or repressed enhancers. In summary, our model produced accurate annotation of enhancers with detailed information on how histone profiles contribute to the presence of putative enhancers.