EnContact: predicting enhancer-enhancer contacts using sequence-based deep learning model

Mingxin Gan; Wenran Li; Rui Jiang

doi:10.7717/peerj.7657

EnContact: predicting enhancer-enhancer contacts using sequence-based deep learning model

PeerJ. 2019 Sep 13:7:e7657. doi: 10.7717/peerj.7657. eCollection 2019.

Authors

Mingxin Gan^#¹, Wenran Li^#^{2

3

4}, Rui Jiang²

Affiliations

¹ Donlinks School of Economics and Management, University of Science and Technology Beijing, Beijing, China.
² MOE Key Laboratory of Bioinformatics; Bioinformatics Division and Center for Synthetic and Systems Biology, BNRist; Department of Automation, Tsinghua University, Beijing, China.
³ Department of Statistics, Stanford University, Stanford, CA, USA.
⁴ Department of Biomedical Data Science, Stanford University, Stanford, CA, USA.

^# Contributed equally.

Abstract

Chromatin contacts between regulatory elements are of crucial importance for the interpretation of transcriptional regulation and the understanding of disease mechanisms. However, existing computational methods mainly focus on the prediction of interactions between enhancers and promoters, leaving enhancer-enhancer (E-E) interactions not well explored. In this work, we develop a novel deep learning approach, named Enhancer-enhancer contacts prediction (EnContact), to predict E-E contacts using genomic sequences as input. We statistically demonstrated the predicting ability of EnContact using training sets and testing sets derived from HiChIP data of seven cell lines. We also show that our model significantly outperforms other baseline methods. Besides, our model identifies finer-mapping E-E interactions from region-based chromatin contacts, where each region contains several enhancers. In addition, we identify a class of hub enhancers using the predicted E-E interactions and find that hub enhancers tend to be active across cell lines. We summarize that our EnContact model is capable of predicting E-E interactions using features automatically learned from genomic sequences.

Keywords: Attention-based RNN; Deep learning; Enhancer-enhancer contacts; HiChIP data; Hub enhancers.

Grants and funding

This research was supported by the National Natural Science Foundation of China (Nos. 71871019, 71471016, 61873141 and 61573207), the National Key Research and Development Program of China (No. 2018YFC0910404), and the Tsinghua-Fuzhou Institute for Data Technology. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.