Cheng, J. R. | Search bioRxiv

bioRxiv2020

VEHiCLE: a Variationally Encoded Hi-C Loss Enhancement algorithm

Chromatin conformation plays an important role in a variety of genomic processes. Hi-C is one of the most popular assays for inspecting chromatin conformation. However, the utility of Hi-C contact maps is bottlenecked by resolution. Here we present VEHiCLE, a deep learning algorithm for resolution enhancement of Hi-C contact data. VEHiCLE utilises a variational autoencoder and adversarial training strategy to enhance contact maps, making them more viable for downstream analysis. VEHiCLE expands previous efforts at Hi-C super resolution by providing novel insight into the biologically meaningful and human interpretable feature extraction. Using a variational autoencoder VEHiCLE provides a user tunable, full generative model for generating synthetic Hi-C data while also providing state-of-the-art results in enhancement of Hi-C data across multiple metrics.

genomics↗

bioRxiv2020

Prediction of the 4D Chromosome Structure From Time-Series Hi-C Data

Chromatin conformation plays an important role in a variety of genomic processes. Hi-C Data is frequently used to analyse structural features of chromatin such as AB compartments, topologically associated domains, and 3D structural models. Recently the genomics community has displayed growing interest in chromatin dynamics over time. Here we present 4DMax, a novel method which uses time-series Hi-C data to predict dynamic chromosome conformation. Using both synthetic data and real time-series Hi-C data from processes such as induced pluripotent stem cell reprogramming and cardiomyocyte differentiation, we construct fluid four dimensional models of individual chromosomes. These predicted 4D models effectively interpolate chromatin position across time, permitting prediction of unknown Hi-C contact maps at intermittent time points. Our results demonstrate that 4DMax correctly recovers higher order features of chromatin such as AB compartments and topologically associated domains, even at time points where Hi-C data is not made available to the algorithm. Use of 4DMax may alleviate the cost of expensive Hi-C experiments by interpolating intermediary timepoints while also providing valuable visualization of dynamic chromatin changes.

genomics↗