TempoMAGE: a deep learning framework that exploits the causal dependency between time-series data to predict histone marks in open chromatin regions at time-points with missing ChIP-seq datasets

Abstract

Motivation Identifying histone tail modifications using ChIP-seq is commonly used in time-series experiments in development and disease. These assays, however, cover specific time-points leaving intermediate or early stages with missing information. Although several machine learning methods were developed to predict histone marks, none exploited the dependence that exists in time-series experiments between data generated at specific time-points to extrapolate these findings to time-points where data cannot be generated for lack or scarcity of materials (i.e., early developmental stages). Results Here, we train a deep learning model named TempoMAGE, to predict the presence or absence of H3K27ac in open chromatin regions by integrating information from sequence, gene expression, chromatin accessibility and the estimated change in H3K27ac state from a reference time-point. We show that adding reference time-point information systematically improves the overall model’s performance. Additionally, sequence signatures extracted from our method were exclusive to the training dataset indicating that our model learned data-specific features. As an application, TempoMAGE was able to predict the activity of enhancers from pre-validated in-vivo dataset highlighting its ability to be used for functional annotation of putative enhancers. Availability TempoMAGE is freely available through GitHub at https://github.com/pkhoueiry/TempoMAGE Supplementary information Supplementary data are available at Bioinformatics online.

A temporal in vivo catalog of chromatin accessibility and expression profiles in pineoblastoma reveals a prevalent role for repressor elements

“…We were unable to track the dynamics of active enhancers over time owing to the lack of H3K27ac data at P10 and P49. We had anticipated the scarcity of chromatin that could be extracted at P10 and developed a machine learning algorithm to predict the H3K27ac state in time-series experiments using H3K27ac data from two available time points ( Hallal et al 2021 ). However, we constantly faced unfortunate events in obtaining samples with good enrichment data at P49, which prevented us from using our model.…”