Getting Personal with Epigenetics: Towards Machine-Learning-Assisted Precision Epigenomics

Abstract

Epigenetic modifications are dynamic control mechanisms involved in the regulation of gene expression. Unlike the DNA sequence itself, they vary not only between individuals but also between different cell types of the same individual. Exposure to environmental factors, somatic mutations, and ageing contribute to epigenomic changes over time, which may constitute early hallmarks or causal factors of disease. Epigenetic changes are reversible and, therefore, promising therapeutic targets. However, mapping efforts to determine an individual's cell-type-specific epigenome are constrained by experimental costs. We developed eDICE, an attention-based deep learning model, to impute epigenomic tracks. eDICE achieves improved overall performance compared to previous models on the reference Roadmap epigenomes. Furthermore, we present a proof of concept for the imputation of personalised epigenomic measurements on the ENTEx dataset, where eDICE correctly predicts individual- and cell-type-specific epigenetic patterns. This case study constitutes an important step towards robustly employing machine-learning-based approaches for personalised epigenomics.

Omics Data and Data Representations for Deep Learning-Based Predictive Modeling

“…When dealing with enhancer–promoter interactions (EPI), random train-test splits may lead to one overestimating the model’s accuracy as there is great redundancy of the enhancer and promoter sequences and they may be present in both the training and the test sets. In [ 116 ], an attention-based DL model was developed, namely eDICE, to impute the epigenomics tracks. The model reported a state-of-the-art overall performance, and it was able to correctly predict the individual and cell-type specific epigenetic patterns.…”