Characterizing collaborative transcription regulation with a graph-based deep learning approach

Human epigenome and transcription activities have been characterized by a number of sequence-based deep learning approaches which only utilize the DNA sequences. However, transcription factors interact with each other, and their collaborative regulatory activities go beyond the linear DNA sequence. Therefore leveraging the informative 3D chromatin organization to investigate the collaborations among transcription factors is critical. We developed ECHO, a graph-based neural network, to predict chromatin features and characterize the collaboration among them by incorporating 3D chromatin organization from 200-bp high-resolution Micro-C contact maps. ECHO predicted 2,583 chromatin features with significantly higher average AUROC and AUPR than the best sequence-based model. We observed that chromatin contacts of different distances affected different types of chromatin features' prediction in diverse ways, suggesting complex and divergent collaborative regulatory mechanisms. Moreover, ECHO was interpretable via gradient-based attribution methods. The attributions on chromatin contacts identify important contacts relevant to chromatin features. The attributions on DNA sequences identify TF binding motifs and TF collaborative binding. Furthermore, combining the attributions on contacts and sequences reveals important sequence patterns in the neighborhood which are relevant to target sequence's chromatin feature prediction. The attribution results that reveal TF collaboration activities are provided on a website https://echo.dcmb.med.umich.edu/echo/.

Evolutionary and functional genomics of DNA methylation in maize domestication and improvement

DNA methylation is a ubiquitous chromatin feature, present in 25% of cytosines in the maize genome, but variation and evolution of the methylation landscape during maize domestication remain largely unknown. Here, we leverage whole-genome sequencing (WGS) and whole-genome bisulfite sequencing (WGBS) data on populations of modern maize, landrace, and teosinte (Zea mays ssp. parviglumis) to estimate epimutation rates and selection coefficients. We find weak evidence for direct selection on DNA methylation in any context, but thousands of differentially methylated regions (DMRs) are identified population-wide that are correlated with recent selection. For two trait-associated DMRs, vgt1-DMR and tb1-DMR, HiChIP data indicate that the interactive loops between DMRs and respective downstream genes are present in B73, a modern maize line, but absent in teosinte. Our results enable a better understanding of the evolutionary forces acting on patterns of DNA methylation and suggest a role of methylation variation in adaptive evolution.

Enhancer prediction in the human genome by probabilistic modelling of the chromatin feature patterns

BackgroundThe binding sites of transcription factors (TFs) and the localisation of histone modifications in the human genome can be quantified by the chromatin immunoprecipitation assay coupled with next-generation sequencing (ChIP-seq). The resulting chromatin feature data has been successfully adopted for genome-wide enhancer identification by several unsupervised and supervised machine learning methods. However, the current methods predict different numbers and different sets of enhancers for the same cell type and do not utilise the pattern of the ChIP-seq coverage profiles efficiently.ResultsIn this work, we propose a PRobabilistic Enhancer PRedictIoN Tool (PREPRINT) that assumes characteristic coverage patterns of chromatin features at enhancers and employs a statistical model to account for their variability. PREPRINT defines probabilistic distance measures to quantify the similarity of the genomic query regions and the characteristic coverage patterns. The probabilistic scores of the enhancer and non-enhancer samples are utilised to train a kernel-based classifier. The performance of the method is demonstrated on ENCODE data for two cell lines. The predicted enhancers are computationally validated based on the transcriptional regulatory protein binding sites and compared to the predictions obtained by state-of-the-art methods.ConclusionPREPRINT performs favorably to the state-of-the-art methods, especially when requiring the methods to predict a larger set of enhancers. PREPRINT generalises successfully to data from cell type not utilised for training, and often the PREPRINT performs better than the previous methods. The PREPRINT enhancers are less sensitive to the choice of prediction threshold. PREPRINT identifies biologically validated enhancers not predicted by the competing methods. The enhancers predicted by PREPRINT can aid the genome interpretation in functional genomics and clinical studies.Availabilityhttps://github.com/MariaOsmala/[email protected]