Connecting high-resolution 3D chromatin organization with epigenomics

While large-scale 3D genome architecture is well studied, the limits of resolution have hindered our understanding on the fine scale. Here the authors mapped 1D epigenomic profiles to fine-scale 3D chromatin structures with their deep learning model CAESAR. The model predicted fine-scale structures, such as short-range chromatin loops and stripes, that Hi-C datasets fail to detect. The resolution of chromatin conformation capture technologies keeps increasing, and the recent nucleosome resolution chromatin contact maps allow us to explore how fine-scale 3D chromatin organization is related to epigenomic states in human cells. Using publicly available Micro-C datasets, we develop a deep learning model, CAESAR, to learn a mapping function from epigenomic features to 3D chromatin organization. The model accurately predicts fine-scale structures, such as short-range chromatin loops and stripes, that Hi-C fails to detect. With existing epigenomic datasets from ENCODE and Roadmap Epigenomics Project, we successfully impute high-resolution 3D chromatin contact maps for 91 human tissues and cell lines. In the imputed high-resolution contact maps, we identify the spatial interactions between genes and their experimentally validated regulatory elements, demonstrating CAESAR's potential in coupling transcriptional regulation with 3D chromatin organization at high resolution.

Automated summary

While large-scale 3D genome architecture is well studied, the authors developed a deep learning model CAESAR to map 1D epigenomic profiles to fine-scale 3D chromatin structures, accurately predicting structures that were missed by Hi-C datasets. They successfully imputed high-resolution 3D chromatin contact maps for 91 human tissues and cell lines, demonstrating the potential of CAESAR in coupling transcriptional regulation with 3D chromatin organization at high resolution.