Predicting Enhancer-Promoter Interaction from Genomic Sequence with Deep Neural Networks

In the human genome, distal enhancers are involved in regulating target genes through proximal promoters by forming enhancer-promoter interactions. However, although recently developed high-throughput experimental approaches have allowed us to recognize potential enhancer-promoter interactions genome-wide, it is still largely unknown whether there are sequence-level instructions encoded in our genome that help govern such interactions. Here we report a new computational method (named “SPEID”) using deep learning models to predict enhancer-promoter interactions based on sequence-based features only, when the locations of putative enhancers and promoters in a particular cell type are given. Our results across six different cell types demonstrate that SPEID is effective in predicting enhancer-promoter interactions as compared to state-of-the-art methods that use non-sequence features from functional genomic signals. This work shows for the first time that sequence-based features alone can reliably predict enhancer-promoter interactions genome-wide, which provides important insights into the sequence determinants for long-range gene regulation.